Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5922 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.2196. Min Act: -0.1700
Data Index: 3516029 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1881. Min Act: -0.1700
Data Index: 7867513 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1881. Min Act: -0.1700
Data Index: 8314401 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1881. Min Act: -0.1700
Data Index: 190153 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1724. Min Act: -0.1700
Data Index: 6150635 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1567. Min Act: -0.1700
Data Index: 882893 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1567. Min Act: -0.1700
Data Index: 7652153 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1409. Min Act: -0.1700
Data Index: 2208146 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1567. Min Act: -0.1700
Data Index: 1388652 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1409. Min Act: -0.1700
Data Index: 6183548 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1567. Min Act: -0.1700
Data Index: 6447425 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1567. Min Act: -0.1700
Data Index: 647169 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1409. Min Act: -0.1700
Data Index: 2942598 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1409. Min Act: -0.1700
Data Index: 1263971 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1409. Min Act: -0.1700
Data Index: 8340035 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1409. Min Act: -0.1700
Data Index: 1946549 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1567. Min Act: -0.1700
Data Index: 1889414 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1409. Min Act: -0.1700
Data Index: 154938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1409. Min Act: -0.1700
Data Index: 2687342 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2196. Min Range: -3.2196
Max Act: 3.1252. Min Act: -0.1700
Data Index: 2864034 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19