Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.4055. Min Act: -0.1700
Data Index: 7408298 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.4055. Min Act: -0.1700
Data Index: 611510 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.4055. Min Act: -0.1700
Data Index: 5743779 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.3430. Min Act: -0.1700
Data Index: 5385326 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.2805. Min Act: -0.1700
Data Index: 8336573 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.3430. Min Act: -0.1700
Data Index: 5150489 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.3430. Min Act: -0.1700
Data Index: 4680852 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.2805. Min Act: -0.1700
Data Index: 5254181 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.2805. Min Act: -0.1700
Data Index: 25254 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.2180. Min Act: -0.1700
Data Index: 5604630 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.0930. Min Act: -0.1700
Data Index: 6808080 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 6619525 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 759688 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 3674026 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 3483147 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 1949100 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 6291023 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 73780 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 1148534 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4055. Min Range: -9.4055
Max Act: 9.1555. Min Act: -0.1700
Data Index: 3379312 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19