Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1634 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.8148. Min Act: -0.1700
Data Index: 3384808 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.3773. Min Act: -0.1700
Data Index: 8185870 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.2523. Min Act: -0.1700
Data Index: 6182128 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.2523. Min Act: -0.1700
Data Index: 2261342 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.2523. Min Act: -0.1700
Data Index: 5432419 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.2523. Min Act: -0.1700
Data Index: 4970345 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.2523. Min Act: -0.1700
Data Index: 2806635 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.1273. Min Act: -0.1700
Data Index: 8578807 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.0648. Min Act: -0.1700
Data Index: 3609239 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.0961. Min Act: -0.1700
Data Index: 115457 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8148. Min Range: -8.8148
Max Act: 8.0336. Min Act: -0.1700
Data Index: 3844081 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.9711. Min Act: -0.1700
Data Index: 576967 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.9086. Min Act: -0.1700
Data Index: 7635806 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.9086. Min Act: -0.1700
Data Index: 5306685 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.8773. Min Act: -0.1700
Data Index: 2757738 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.8773. Min Act: -0.1700
Data Index: 5684476 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.8461. Min Act: -0.1700
Data Index: 621474 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.8461. Min Act: -0.1700
Data Index: 6771288 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.8148. Min Act: -0.1700
Data Index: 5390572 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8148. Min Range: -8.8148
Max Act: 7.8148. Min Act: -0.1700
Data Index: 3990894 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19