Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1191. Min Range: -8.1191
Max Act: 8.1191. Min Act: -0.1700
Data Index: 2875160 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.8691. Min Act: -0.1700
Data Index: 2450708 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.8066. Min Act: -0.1700
Data Index: 7340685 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.8066. Min Act: -0.1700
Data Index: 4237861 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.7441. Min Act: -0.1700
Data Index: 2074985 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.6816. Min Act: -0.1700
Data Index: 6545349 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.6816. Min Act: -0.1700
Data Index: 1654761 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.6191. Min Act: -0.1700
Data Index: 5742825 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.5566. Min Act: -0.1700
Data Index: 6201182 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.5566. Min Act: -0.1700
Data Index: 6435096 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.5566. Min Act: -0.1700
Data Index: 1959908 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.6191. Min Act: -0.1700
Data Index: 3751940 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.6191. Min Act: -0.1700
Data Index: 7316448 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.4941. Min Act: -0.1700
Data Index: 1806993 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.4941. Min Act: -0.1700
Data Index: 6377523 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.4316. Min Act: -0.1700
Data Index: 2582306 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.4941. Min Act: -0.1700
Data Index: 1296132 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.4941. Min Act: -0.1700
Data Index: 919420 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.4941. Min Act: -0.1700
Data Index: 5324265 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1191. Min Range: -8.1191
Max Act: 7.4316. Min Act: -0.1700
Data Index: 6285402 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19