Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 255 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.5782. Min Act: -0.1700
Data Index: 457652 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.5520. Min Act: -0.1700
Data Index: 6441761 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.5345. Min Act: -0.1700
Data Index: 6168894 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.5257. Min Act: -0.1700
Data Index: 3096071 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4818. Min Act: -0.1700
Data Index: 5436351 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4818. Min Act: -0.1700
Data Index: 3370769 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4730. Min Act: -0.1700
Data Index: 1386816 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4642. Min Act: -0.1699
Data Index: 6062215 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4642. Min Act: -0.1700
Data Index: 2148858 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4466. Min Act: -0.1700
Data Index: 664984 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4466. Min Act: -0.1700
Data Index: 7850698 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4466. Min Act: -0.1700
Data Index: 6994440 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4554. Min Act: -0.1700
Data Index: 3061912 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4466. Min Act: -0.1693
Data Index: 4975108 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4466. Min Act: -0.1700
Data Index: 664986 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4466. Min Act: -0.1700
Data Index: 5891988 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4466. Min Act: -0.1700
Data Index: 2148856 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4290. Min Act: -0.1700
Data Index: 4113927 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4378. Min Act: -0.1699
Data Index: 2069857 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5782. Min Range: -1.5782
Max Act: 1.4378. Min Act: -0.1700
Data Index: 5233944 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19