Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1604 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.8682. Min Act: -0.1700
Data Index: 6596066 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.8526. Min Act: -0.1700
Data Index: 4700341 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.7588. Min Act: -0.1700
Data Index: 8235622 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.7588. Min Act: -0.1700
Data Index: 4483547 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.6649. Min Act: -0.1700
Data Index: 4453952 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.6493. Min Act: -0.1700
Data Index: 7306094 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5867. Min Act: -0.1700
Data Index: 4149708 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.6023. Min Act: -0.1700
Data Index: 5371615 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5867. Min Act: -0.1700
Data Index: 5363528 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5710. Min Act: -0.1700
Data Index: 3356069 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5710. Min Act: -0.1700
Data Index: 5726575 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5710. Min Act: -0.1700
Data Index: 6560281 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5397. Min Act: -0.1700
Data Index: 1055517 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5084. Min Act: -0.1700
Data Index: 632904 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5084. Min Act: -0.1700
Data Index: 151303 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5084. Min Act: -0.1700
Data Index: 6102094 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5084. Min Act: -0.1700
Data Index: 4807608 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.5084. Min Act: -0.1700
Data Index: 3348089 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.4927. Min Act: -0.1700
Data Index: 2005861 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8682. Min Range: -3.8682
Max Act: 3.4927. Min Act: -0.1700
Data Index: 642713 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19