Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2425. Min Range: -4.2425
Max Act: 4.2425. Min Act: -0.1700
Data Index: 4352055 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2425. Min Range: -4.2425
Max Act: 4.1800. Min Act: -0.1700
Data Index: 4322622 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2425. Min Range: -4.2425
Max Act: 4.1175. Min Act: -0.1700
Data Index: 267886 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2425. Min Range: -4.2425
Max Act: 4.1175. Min Act: -0.1700
Data Index: 7299187 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2425. Min Range: -4.2425
Max Act: 4.1175. Min Act: -0.1700
Data Index: 3439263 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2425. Min Range: -4.2425
Max Act: 4.1175. Min Act: -0.1700
Data Index: 682218 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2425. Min Range: -4.2425
Max Act: 4.0550. Min Act: -0.1700
Data Index: 4355242 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9925. Min Act: -0.1700
Data Index: 6953012 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9925. Min Act: -0.1700
Data Index: 7891342 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9612. Min Act: -0.1700
Data Index: 2983071 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9925. Min Act: -0.1700
Data Index: 3969528 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9612. Min Act: -0.1700
Data Index: 4435182 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9925. Min Act: -0.1700
Data Index: 2010712 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9612. Min Act: -0.1700
Data Index: 5934657 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9300. Min Act: -0.1700
Data Index: 6243944 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9300. Min Act: -0.1700
Data Index: 5428502 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9300. Min Act: -0.1700
Data Index: 6271968 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9300. Min Act: -0.1700
Data Index: 3066253 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9300. Min Act: -0.1700
Data Index: 356634 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2425. Min Range: -4.2425
Max Act: 3.9300. Min Act: -0.1700
Data Index: 5223250 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19