Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5390 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.9412. Min Act: -0.1700
Data Index: 4267049 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.8787. Min Act: -0.1700
Data Index: 6957169 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.9412. Min Act: -0.1700
Data Index: 2994694 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.8162. Min Act: -0.1700
Data Index: 688185 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.7537. Min Act: -0.1700
Data Index: 8782022 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.6912. Min Act: -0.1700
Data Index: 6231561 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.6912. Min Act: -0.1700
Data Index: 8220839 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.6287. Min Act: -0.1700
Data Index: 6862635 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.5974. Min Act: -0.1700
Data Index: 6106517 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.5974. Min Act: -0.1700
Data Index: 3587635 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.5349. Min Act: -0.1700
Data Index: 5148492 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.5349. Min Act: -0.1700
Data Index: 2456077 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.5037. Min Act: -0.1700
Data Index: 8774362 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.4724. Min Act: -0.1700
Data Index: 1602126 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.4412. Min Act: -0.1700
Data Index: 5994528 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.4099. Min Act: -0.1700
Data Index: 8548825 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.4099. Min Act: -0.1700
Data Index: 3251541 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.4099. Min Act: -0.1700
Data Index: 5061063 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.3474. Min Act: -0.1700
Data Index: 6483105 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9412. Min Range: -7.9412
Max Act: 7.3474. Min Act: -0.1700
Data Index: 4358964 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19