Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.4728. Min Act: -0.1700
Data Index: 604684 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.4103. Min Act: -0.1700
Data Index: 2974814 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.2853. Min Act: -0.1700
Data Index: 7424866 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.1915. Min Act: -0.1700
Data Index: 1350224 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.1603. Min Act: -0.1700
Data Index: 974465 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.1290. Min Act: -0.1700
Data Index: 4030367 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.1290. Min Act: -0.1700
Data Index: 6127877 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.1290. Min Act: -0.1700
Data Index: 1552931 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0978. Min Act: -0.1700
Data Index: 3674527 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0978. Min Act: -0.1700
Data Index: 1007974 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0978. Min Act: -0.1700
Data Index: 1839412 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0665. Min Act: -0.1700
Data Index: 8524718 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0353. Min Act: -0.1700
Data Index: 5509175 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0665. Min Act: -0.1700
Data Index: 697048 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0665. Min Act: -0.1700
Data Index: 4587097 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0353. Min Act: -0.1700
Data Index: 1845130 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0353. Min Act: -0.1700
Data Index: 3068638 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0353. Min Act: -0.1700
Data Index: 7643761 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0353. Min Act: -0.1700
Data Index: 2792494 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4728. Min Range: -6.4728
Max Act: 6.0665. Min Act: -0.1700
Data Index: 7227162 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19