Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.5211. Min Range: -10.5211
Max Act: 10.5211. Min Act: -0.1700
Data Index: 1344265 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.9586. Min Act: -0.1700
Data Index: 419058 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.9586. Min Act: -0.1700
Data Index: 8797800 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.8336. Min Act: -0.1700
Data Index: 527260 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.6461. Min Act: -0.1700
Data Index: 5584494 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.6461. Min Act: -0.1700
Data Index: 5852065 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.6461. Min Act: -0.1700
Data Index: 3564468 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.6461. Min Act: -0.1700
Data Index: 6212193 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.5211. Min Act: -0.1700
Data Index: 4411554 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.4586. Min Act: -0.1700
Data Index: 1985170 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.4586. Min Act: -0.1700
Data Index: 708947 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.4586. Min Act: -0.1700
Data Index: 5627413 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.4586. Min Act: -0.1700
Data Index: 6460979 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.4586. Min Act: -0.1700
Data Index: 5949159 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.3961. Min Act: -0.1700
Data Index: 2600670 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.4586. Min Act: -0.1700
Data Index: 2206695 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.3336. Min Act: -0.1700
Data Index: 7639709 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.2711. Min Act: -0.1700
Data Index: 7249435 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.2086. Min Act: -0.1700
Data Index: 2951919 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5211. Min Range: -10.5211
Max Act: 9.1461. Min Act: -0.1700
Data Index: 2382728 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19