Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1200 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.3565. Min Act: -0.1700
Data Index: 20170 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.3251. Min Act: -0.1700
Data Index: 1452433 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.2623. Min Act: -0.1700
Data Index: 2886851 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.2152. Min Act: -0.1700
Data Index: 467276 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.2152. Min Act: -0.1700
Data Index: 5488297 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1680. Min Act: -0.1700
Data Index: 1063076 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1522. Min Act: -0.1700
Data Index: 1063073 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1680. Min Act: -0.1700
Data Index: 4700826 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1522. Min Act: -0.1700
Data Index: 6127079 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1365. Min Act: -0.1700
Data Index: 3057420 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1365. Min Act: -0.1700
Data Index: 8305975 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1208. Min Act: -0.1700
Data Index: 4506806 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1365. Min Act: -0.1700
Data Index: 467279 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1050. Min Act: -0.1700
Data Index: 2886853 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1208. Min Act: -0.1700
Data Index: 4506804 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.1050. Min Act: -0.1700
Data Index: 891478 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.0892. Min Act: -0.1700
Data Index: 5923869 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.0735. Min Act: -0.1700
Data Index: 6902492 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.0892. Min Act: -0.1700
Data Index: 2262037 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3565. Min Range: -3.3565
Max Act: 3.0735. Min Act: -0.1700
Data Index: 1063075 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19