Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.8498. Min Act: -0.1700
Data Index: 1113954 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.8498. Min Act: -0.1700
Data Index: 5606191 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.8028. Min Act: -0.1700
Data Index: 3259165 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.8185. Min Act: -0.1700
Data Index: 5877401 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.8185. Min Act: -0.1700
Data Index: 3470746 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.7559. Min Act: -0.1700
Data Index: 7950393 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.7559. Min Act: -0.1700
Data Index: 2235794 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.7090. Min Act: -0.1700
Data Index: 7620605 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.7090. Min Act: -0.1700
Data Index: 6188214 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6777. Min Act: -0.1700
Data Index: 7910485 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6621. Min Act: -0.1700
Data Index: 7090081 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6621. Min Act: -0.1700
Data Index: 4323681 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6621. Min Act: -0.1700
Data Index: 1691816 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6777. Min Act: -0.1700
Data Index: 6534187 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6621. Min Act: -0.1700
Data Index: 1884120 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6621. Min Act: -0.1700
Data Index: 841190 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6621. Min Act: -0.1700
Data Index: 2408168 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6464. Min Act: -0.1700
Data Index: 7348333 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6464. Min Act: -0.1700
Data Index: 2255810 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8498. Min Range: -3.8498
Max Act: 3.6308. Min Act: -0.1700
Data Index: 2002624 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19