Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2474 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.9652. Min Act: -0.1700
Data Index: 3032394 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.9027. Min Act: -0.1700
Data Index: 7192456 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.8402. Min Act: -0.1700
Data Index: 269335 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.7152. Min Act: -0.1700
Data Index: 6875802 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.6214. Min Act: -0.1700
Data Index: 3102569 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.5902. Min Act: -0.1700
Data Index: 1600580 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.6214. Min Act: -0.1700
Data Index: 4149712 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.5902. Min Act: -0.1700
Data Index: 4096505 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.5277. Min Act: -0.1700
Data Index: 6692165 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.5277. Min Act: -0.1700
Data Index: 7932237 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.5277. Min Act: -0.1700
Data Index: 5084512 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.5277. Min Act: -0.1700
Data Index: 6446124 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.4652. Min Act: -0.1700
Data Index: 445638 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.4964. Min Act: -0.1700
Data Index: 834791 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.4339. Min Act: -0.1700
Data Index: 5624184 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.3714. Min Act: -0.1700
Data Index: 7534944 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.3714. Min Act: -0.1700
Data Index: 7148485 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.3402. Min Act: -0.1700
Data Index: 5520058 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.3402. Min Act: -0.1700
Data Index: 3348188 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9652. Min Range: -7.9652
Max Act: 7.3089. Min Act: -0.1700
Data Index: 6391275 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19