Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2085 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.2630. Min Act: -0.1700
Data Index: 5572211 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.2005. Min Act: -0.1700
Data Index: 588410 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.2630. Min Act: -0.1700
Data Index: 1472799 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.1692. Min Act: -0.1700
Data Index: 7151137 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.1379. Min Act: -0.1700
Data Index: 4261119 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.1379. Min Act: -0.1700
Data Index: 6217991 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.0754. Min Act: -0.1700
Data Index: 3250625 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.1067. Min Act: -0.1700
Data Index: 5630163 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.0754. Min Act: -0.1700
Data Index: 5035713 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.0442. Min Act: -0.1700
Data Index: 1946450 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.0129. Min Act: -0.1700
Data Index: 730917 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.0129. Min Act: -0.1700
Data Index: 1976795 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2630. Min Range: -4.2630
Max Act: 4.0129. Min Act: -0.1700
Data Index: 8124415 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2630. Min Range: -4.2630
Max Act: 3.9817. Min Act: -0.1700
Data Index: 4262027 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2630. Min Range: -4.2630
Max Act: 3.9504. Min Act: -0.1700
Data Index: 2466286 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2630. Min Range: -4.2630
Max Act: 3.9504. Min Act: -0.1700
Data Index: 3555886 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2630. Min Range: -4.2630
Max Act: 3.9191. Min Act: -0.1700
Data Index: 7325984 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2630. Min Range: -4.2630
Max Act: 3.9504. Min Act: -0.1700
Data Index: 337882 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2630. Min Range: -4.2630
Max Act: 3.8879. Min Act: -0.1700
Data Index: 4563162 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2630. Min Range: -4.2630
Max Act: 3.9191. Min Act: -0.1700
Data Index: 5686524 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19