Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.5086. Min Act: -0.1700
Data Index: 3826858 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.5398. Min Act: -0.1700
Data Index: 4852509 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.4148. Min Act: -0.1700
Data Index: 6419935 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.3523. Min Act: -0.1700
Data Index: 7602196 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.3836. Min Act: -0.1700
Data Index: 8210987 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.3211. Min Act: -0.1700
Data Index: 8105355 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.2898. Min Act: -0.1700
Data Index: 3405004 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.2586. Min Act: -0.1700
Data Index: 8152446 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.2586. Min Act: -0.1700
Data Index: 758551 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.2586. Min Act: -0.1700
Data Index: 1030612 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.2273. Min Act: -0.1700
Data Index: 2933235 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.2273. Min Act: -0.1700
Data Index: 1578658 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.2273. Min Act: -0.1700
Data Index: 1294589 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.1961. Min Act: -0.1700
Data Index: 7213456 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.1961. Min Act: -0.1700
Data Index: 2844059 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.1961. Min Act: -0.1700
Data Index: 5505397 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.1648. Min Act: -0.1700
Data Index: 1850515 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.1648. Min Act: -0.1700
Data Index: 2143779 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.1648. Min Act: -0.1700
Data Index: 4272577 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5398. Min Range: -5.5398
Max Act: 5.1961. Min Act: -0.1700
Data Index: 6452257 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19