Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1962. Min Act: -0.1700
Data Index: 6484013 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1962. Min Act: -0.1700
Data Index: 3964836 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1962. Min Act: -0.1700
Data Index: 7985193 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1962. Min Act: -0.1700
Data Index: 8807048 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1962. Min Act: -0.1700
Data Index: 3350799 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1337. Min Act: -0.1700
Data Index: 7612146 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1337. Min Act: -0.1700
Data Index: 1205129 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1649. Min Act: -0.1700
Data Index: 8693170 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1649. Min Act: -0.1700
Data Index: 5151152 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1962. Min Act: -0.1700
Data Index: 3378326 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1337. Min Act: -0.1700
Data Index: 3853811 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1337. Min Act: -0.1700
Data Index: 1223845 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1337. Min Act: -0.1700
Data Index: 5862118 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1337. Min Act: -0.1700
Data Index: 8247361 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1024. Min Act: -0.1700
Data Index: 2121338 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1024. Min Act: -0.1700
Data Index: 675623 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.0712. Min Act: -0.1700
Data Index: 6381866 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1024. Min Act: -0.1700
Data Index: 2114861 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1024. Min Act: -0.1700
Data Index: 149200 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1962. Min Range: -5.1962
Max Act: 5.1024. Min Act: -0.1700
Data Index: 5668043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19