Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 82 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.6152. Min Act: -0.1700
Data Index: 196888 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.1575. Min Act: -0.1700
Data Index: 4914469 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.1241. Min Act: -0.1700
Data Index: 6628786 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.1241. Min Act: -0.1700
Data Index: 7712432 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.1241. Min Act: -0.1700
Data Index: 2002724 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.1074. Min Act: -0.1700
Data Index: 4374029 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.1074. Min Act: -0.1696
Data Index: 4188434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.1074. Min Act: -0.1700
Data Index: 3433454 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0907. Min Act: -0.1700
Data Index: 7657620 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0571. Min Act: -0.1700
Data Index: 1614842 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0739. Min Act: -0.1700
Data Index: 6439346 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0739. Min Act: -0.1700
Data Index: 4802085 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0907. Min Act: -0.1700
Data Index: 7898276 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0739. Min Act: -0.1700
Data Index: 7860355 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0571. Min Act: -0.1700
Data Index: 5047411 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0571. Min Act: -0.1700
Data Index: 3584322 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0403. Min Act: -0.1700
Data Index: 3672136 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0739. Min Act: -0.1700
Data Index: 6409730 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0571. Min Act: -0.1700
Data Index: 3702239 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6152. Min Range: -2.6152
Max Act: 2.0571. Min Act: -0.1700
Data Index: 5648112 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19