Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2473 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.7673. Min Act: -0.1700
Data Index: 1988672 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.6423. Min Act: -0.1700
Data Index: 6639285 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.5486. Min Act: -0.1700
Data Index: 1988673 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.4861. Min Act: -0.1700
Data Index: 1437974 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.4861. Min Act: -0.1700
Data Index: 3129093 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.4861. Min Act: -0.1700
Data Index: 5635734 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.3923. Min Act: -0.1700
Data Index: 5005290 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.4236. Min Act: -0.1700
Data Index: 2748767 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.3611. Min Act: -0.1700
Data Index: 8511924 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.3611. Min Act: -0.1700
Data Index: 407984 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.3298. Min Act: -0.1700
Data Index: 46491 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.3298. Min Act: -0.1700
Data Index: 2839210 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 4621902 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 240146 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 3798581 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 1096510 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 258446 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.2048. Min Act: -0.1700
Data Index: 1836484 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.2048. Min Act: -0.1700
Data Index: 3656153 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7673. Min Range: -4.7673
Max Act: 4.2360. Min Act: -0.1700
Data Index: 5041773 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19