Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3695 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.9505. Min Act: -0.1700
Data Index: 4521709 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.8255. Min Act: -0.1700
Data Index: 788063 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.5755. Min Act: -0.1700
Data Index: 1970362 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.5755. Min Act: -0.1700
Data Index: 883828 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.5755. Min Act: -0.1696
Data Index: 6953827 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.5755. Min Act: -0.1700
Data Index: 2691480 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.5755. Min Act: -0.1697
Data Index: 4258527 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.5755. Min Act: -0.1643
Data Index: 3160247 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.4505. Min Act: -0.1698
Data Index: 2025559 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.4505. Min Act: -0.1700
Data Index: 3194619 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.4505. Min Act: -0.1700
Data Index: 8125060 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.3255. Min Act: -0.1699
Data Index: 1673577 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.3255. Min Act: -0.1609
Data Index: 1771541 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.3255. Min Act: -0.1700
Data Index: 3560586 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.3255. Min Act: -0.1700
Data Index: 4258526 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.3255. Min Act: -0.1700
Data Index: 7913592 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.3255. Min Act: -0.1700
Data Index: 3958679 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.4505. Min Act: -0.1700
Data Index: 7746198 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.3255. Min Act: -0.1700
Data Index: 6057435 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.9505. Min Range: -19.9505
Max Act: 19.2005. Min Act: -0.1700
Data Index: 4577988 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19