Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 620 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2192. Min Range: -8.2192
Max Act: 8.2192. Min Act: -0.1700
Data Index: 489122 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.8442. Min Act: -0.1700
Data Index: 3993638 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.7817. Min Act: -0.1700
Data Index: 7362091 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.7817. Min Act: -0.1700
Data Index: 3528127 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.7504. Min Act: -0.1700
Data Index: 5637953 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.7192. Min Act: -0.1700
Data Index: 6900618 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.6254. Min Act: -0.1700
Data Index: 197606 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.6879. Min Act: -0.1700
Data Index: 6507034 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.6254. Min Act: -0.1700
Data Index: 1151935 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.6567. Min Act: -0.1700
Data Index: 7447616 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.6254. Min Act: -0.1700
Data Index: 1697850 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.5629. Min Act: -0.1700
Data Index: 6824913 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.5004. Min Act: -0.1700
Data Index: 942671 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.4692. Min Act: -0.1700
Data Index: 2521726 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.4692. Min Act: -0.1700
Data Index: 4280790 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.4067. Min Act: -0.1700
Data Index: 3400020 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.4379. Min Act: -0.1700
Data Index: 1675513 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.4379. Min Act: -0.1700
Data Index: 6856951 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.4067. Min Act: -0.1700
Data Index: 4671999 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2192. Min Range: -8.2192
Max Act: 7.4067. Min Act: -0.1700
Data Index: 4644987 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19