Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3793 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0582. Min Range: -5.0582
Max Act: 5.0270. Min Act: -0.1700
Data Index: 3530232 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0582. Min Range: -5.0582
Max Act: 5.0582. Min Act: -0.1700
Data Index: 4605263 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0582. Min Range: -5.0582
Max Act: 5.0270. Min Act: -0.1700
Data Index: 5936654 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9957. Min Act: -0.1700
Data Index: 4179779 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9957. Min Act: -0.1700
Data Index: 3448536 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9957. Min Act: -0.1700
Data Index: 4029148 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9645. Min Act: -0.1700
Data Index: 6103240 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9957. Min Act: -0.1700
Data Index: 3450205 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9645. Min Act: -0.1700
Data Index: 4179780 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9645. Min Act: -0.1700
Data Index: 6831504 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9332. Min Act: -0.1700
Data Index: 3585204 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9332. Min Act: -0.1700
Data Index: 3684001 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9020. Min Act: -0.1700
Data Index: 892651 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9020. Min Act: -0.1700
Data Index: 3141430 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9020. Min Act: -0.1700
Data Index: 8480670 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9020. Min Act: -0.1700
Data Index: 6662117 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9020. Min Act: -0.1700
Data Index: 7960937 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9020. Min Act: -0.1700
Data Index: 6630280 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.9020. Min Act: -0.1700
Data Index: 6115621 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0582. Min Range: -5.0582
Max Act: 4.8395. Min Act: -0.1700
Data Index: 364252 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19