Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.9941. Min Act: -0.1700
Data Index: 2723268 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.8691. Min Act: -0.1700
Data Index: 393559 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.7754. Min Act: -0.1700
Data Index: 136659 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.7129. Min Act: -0.1700
Data Index: 8605399 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.6816. Min Act: -0.1700
Data Index: 6235989 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.6504. Min Act: -0.1700
Data Index: 785624 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.6191. Min Act: -0.1700
Data Index: 556008 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.6191. Min Act: -0.1700
Data Index: 785625 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.6191. Min Act: -0.1700
Data Index: 4263935 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5879. Min Act: -0.1700
Data Index: 4738477 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5879. Min Act: -0.1700
Data Index: 201402 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5879. Min Act: -0.1700
Data Index: 7524915 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5879. Min Act: -0.1700
Data Index: 7646696 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5566. Min Act: -0.1700
Data Index: 4671066 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5566. Min Act: -0.1700
Data Index: 8175196 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5566. Min Act: -0.1700
Data Index: 4841447 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5566. Min Act: -0.1700
Data Index: 3835483 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5566. Min Act: -0.1700
Data Index: 952585 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.5566. Min Act: -0.1700
Data Index: 2891223 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9941. Min Range: -4.9941
Max Act: 4.4941. Min Act: -0.1700
Data Index: 5472474 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19