Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3987 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.9114. Min Act: -0.1700
Data Index: 2512343 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.7864. Min Act: -0.1700
Data Index: 3217373 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.5364. Min Act: -0.1700
Data Index: 241613 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.4739. Min Act: -0.1700
Data Index: 4454624 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.4739. Min Act: -0.1700
Data Index: 1602709 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.4739. Min Act: -0.1700
Data Index: 1177828 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.2239. Min Act: -0.1700
Data Index: 7788840 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.2239. Min Act: -0.1700
Data Index: 2370761 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.2239. Min Act: -0.1700
Data Index: 5457114 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.1614. Min Act: -0.1700
Data Index: 3494533 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.1614. Min Act: -0.1700
Data Index: 608677 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.1614. Min Act: -0.1700
Data Index: 2809655 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.1614. Min Act: -0.1700
Data Index: 5767963 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.1614. Min Act: -0.1700
Data Index: 5991593 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.1614. Min Act: -0.1700
Data Index: 799791 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.1614. Min Act: -0.1700
Data Index: 5918556 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.1614. Min Act: -0.1700
Data Index: 8154989 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.0989. Min Act: -0.1700
Data Index: 6522194 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.0989. Min Act: -0.1700
Data Index: 2361161 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9114. Min Range: -11.9114
Max Act: 11.0989. Min Act: -0.1700
Data Index: 7641897 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19