Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1498. Min Range: -6.1498
Max Act: 6.1186. Min Act: -0.1700
Data Index: 2635661 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1498. Min Range: -6.1498
Max Act: 6.1498. Min Act: -0.1700
Data Index: 7072553 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1498. Min Range: -6.1498
Max Act: 6.1186. Min Act: -0.1700
Data Index: 5724054 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.9623. Min Act: -0.1700
Data Index: 4756026 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.8686. Min Act: -0.1700
Data Index: 8151923 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.8373. Min Act: -0.1700
Data Index: 8448666 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.8373. Min Act: -0.1700
Data Index: 1303806 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.7436. Min Act: -0.1700
Data Index: 4213335 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.7436. Min Act: -0.1700
Data Index: 2910201 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.7436. Min Act: -0.1700
Data Index: 3195813 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.7436. Min Act: -0.1700
Data Index: 5756109 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.7123. Min Act: -0.1700
Data Index: 8349903 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.6811. Min Act: -0.1700
Data Index: 6989598 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.6811. Min Act: -0.1700
Data Index: 1054877 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.6811. Min Act: -0.1700
Data Index: 1094260 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.6498. Min Act: -0.1700
Data Index: 1250607 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.6498. Min Act: -0.1700
Data Index: 5679794 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.6498. Min Act: -0.1700
Data Index: 148913 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.6498. Min Act: -0.1700
Data Index: 8295534 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1498. Min Range: -6.1498
Max Act: 5.6186. Min Act: -0.1700
Data Index: 2730699 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19