Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0315. Min Range: -6.0315
Max Act: 6.0315. Min Act: -0.1700
Data Index: 586000 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.9690. Min Act: -0.1700
Data Index: 6882259 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.9065. Min Act: -0.1700
Data Index: 64813 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.8752. Min Act: -0.1700
Data Index: 6536274 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.8127. Min Act: -0.1700
Data Index: 2604207 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.7815. Min Act: -0.1700
Data Index: 8831531 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.7815. Min Act: -0.1700
Data Index: 1977664 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.7815. Min Act: -0.1700
Data Index: 3610009 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.7190. Min Act: -0.1700
Data Index: 3814945 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.6877. Min Act: -0.1700
Data Index: 1825551 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.6877. Min Act: -0.1700
Data Index: 1124110 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.6565. Min Act: -0.1700
Data Index: 968166 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.6565. Min Act: -0.1700
Data Index: 12488 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.6252. Min Act: -0.1700
Data Index: 589172 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.5940. Min Act: -0.1700
Data Index: 1217501 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.6252. Min Act: -0.1700
Data Index: 6568016 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.5627. Min Act: -0.1700
Data Index: 5680740 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.5627. Min Act: -0.1700
Data Index: 6363435 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.5627. Min Act: -0.1700
Data Index: 3187661 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.5315. Min Act: -0.1700
Data Index: 7011629 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19