Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2068 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.9383. Min Act: -0.1699
Data Index: 2377551 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.9071. Min Act: -0.1700
Data Index: 3527711 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.7508. Min Act: -0.1700
Data Index: 8399641 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.7821. Min Act: -0.1700
Data Index: 3575866 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6883. Min Act: -0.1700
Data Index: 5439861 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.7196. Min Act: -0.1699
Data Index: 1606984 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.7508. Min Act: -0.1700
Data Index: 6615834 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.7196. Min Act: -0.1700
Data Index: 1698209 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.7196. Min Act: -0.1700
Data Index: 2868442 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6883. Min Act: -0.1700
Data Index: 8250296 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6883. Min Act: -0.1700
Data Index: 8662 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6571. Min Act: -0.1700
Data Index: 4612116 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.7196. Min Act: -0.1700
Data Index: 8503041 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.7196. Min Act: -0.1700
Data Index: 2040099 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6571. Min Act: -0.1700
Data Index: 8130593 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6571. Min Act: -0.1700
Data Index: 8692216 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6571. Min Act: -0.1700
Data Index: 6872938 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6258. Min Act: -0.1700
Data Index: 2690792 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6258. Min Act: -0.1700
Data Index: 7913163 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9383. Min Range: -6.9383
Max Act: 6.6258. Min Act: -0.1700
Data Index: 53799 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19