Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.5094. Min Act: -0.1700
Data Index: 994168 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.4781. Min Act: -0.1700
Data Index: 984738 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.4469. Min Act: -0.1700
Data Index: 153102 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.4156. Min Act: -0.1700
Data Index: 227846 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.2594. Min Act: -0.1700
Data Index: 305460 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.2281. Min Act: -0.1699
Data Index: 6223179 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.2281. Min Act: -0.1700
Data Index: 7635504 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.1969. Min Act: -0.1700
Data Index: 4568289 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.1656. Min Act: -0.1700
Data Index: 7635503 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.1344. Min Act: -0.1700
Data Index: 153101 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.0719. Min Act: -0.1700
Data Index: 8176762 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.0719. Min Act: -0.1700
Data Index: 7219969 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.0719. Min Act: -0.1700
Data Index: 3173004 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5094. Min Range: -6.5094
Max Act: 6.0719. Min Act: -0.1700
Data Index: 72382 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5094. Min Range: -6.5094
Max Act: 5.9781. Min Act: -0.1700
Data Index: 2230392 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5094. Min Range: -6.5094
Max Act: 5.9469. Min Act: -0.1700
Data Index: 1327461 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5094. Min Range: -6.5094
Max Act: 5.9156. Min Act: -0.1699
Data Index: 1974210 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5094. Min Range: -6.5094
Max Act: 5.8219. Min Act: -0.1700
Data Index: 8790476 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5094. Min Range: -6.5094
Max Act: 5.8219. Min Act: -0.1700
Data Index: 4807101 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5094. Min Range: -6.5094
Max Act: 5.7906. Min Act: -0.1700
Data Index: 6804580 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19