Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.4277. Min Act: -0.1700
Data Index: 6239540 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.3340. Min Act: -0.1700
Data Index: 5519144 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.3027. Min Act: -0.1700
Data Index: 3593685 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.2090. Min Act: -0.1700
Data Index: 5878409 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.1777. Min Act: -0.1700
Data Index: 8107492 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.1465. Min Act: -0.1700
Data Index: 5332091 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.1465. Min Act: -0.1700
Data Index: 8654902 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.1465. Min Act: -0.1700
Data Index: 761926 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.1152. Min Act: -0.1700
Data Index: 3529948 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.1152. Min Act: -0.1700
Data Index: 5968661 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.0215. Min Act: -0.1700
Data Index: 3536439 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4277. Min Range: -7.4277
Max Act: 6.9902. Min Act: -0.1700
Data Index: 6174270 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4277. Min Range: -7.4277
Max Act: 7.0215. Min Act: -0.1700
Data Index: 8290396 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4277. Min Range: -7.4277
Max Act: 6.9902. Min Act: -0.1700
Data Index: 4795950 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4277. Min Range: -7.4277
Max Act: 6.9590. Min Act: -0.1700
Data Index: 5695970 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4277. Min Range: -7.4277
Max Act: 6.9902. Min Act: -0.1700
Data Index: 1953812 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4277. Min Range: -7.4277
Max Act: 6.9590. Min Act: -0.1700
Data Index: 4981517 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4277. Min Range: -7.4277
Max Act: 6.9590. Min Act: -0.1700
Data Index: 4883647 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4277. Min Range: -7.4277
Max Act: 6.9590. Min Act: -0.1700
Data Index: 4444655 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4277. Min Range: -7.4277
Max Act: 6.9277. Min Act: -0.1700
Data Index: 6784490 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19