Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.7566. Min Act: -0.1700
Data Index: 5374546 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.5691. Min Act: -0.1700
Data Index: 1975483 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.5691. Min Act: -0.1700
Data Index: 6481619 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.5066. Min Act: -0.1700
Data Index: 597665 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.5066. Min Act: -0.1700
Data Index: 2875176 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.4128. Min Act: -0.1700
Data Index: 3159544 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.4128. Min Act: -0.1700
Data Index: 1597176 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3816. Min Act: -0.1700
Data Index: 7730947 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3503. Min Act: -0.1700
Data Index: 2977313 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3503. Min Act: -0.1700
Data Index: 6094487 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3503. Min Act: -0.1700
Data Index: 7616573 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.2253. Min Act: -0.1700
Data Index: 7814390 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.2878. Min Act: -0.1700
Data Index: 2822198 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.1941. Min Act: -0.1700
Data Index: 3715675 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.2253. Min Act: -0.1700
Data Index: 8479907 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.1628. Min Act: -0.1700
Data Index: 13335 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.1941. Min Act: -0.1700
Data Index: 6575288 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.1941. Min Act: -0.1700
Data Index: 6767311 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.1941. Min Act: -0.1700
Data Index: 4195492 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.1316. Min Act: -0.1700
Data Index: 212527 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19