Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5325. Min Range: -10.5325
Max Act: 10.5325. Min Act: -0.1700
Data Index: 5920251 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5325. Min Range: -10.5325
Max Act: 10.2825. Min Act: -0.1700
Data Index: 6082822 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5325. Min Range: -10.5325
Max Act: 10.2200. Min Act: -0.1700
Data Index: 7808477 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5325. Min Range: -10.5325
Max Act: 10.1575. Min Act: -0.1700
Data Index: 1337829 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5325. Min Range: -10.5325
Max Act: 10.0950. Min Act: -0.1700
Data Index: 1928349 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5325. Min Range: -10.5325
Max Act: 10.0325. Min Act: -0.1700
Data Index: 151174 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.9075. Min Act: -0.1700
Data Index: 7344305 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.9075. Min Act: -0.1700
Data Index: 5824134 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.9700. Min Act: -0.1700
Data Index: 1204384 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.9075. Min Act: -0.1700
Data Index: 1784756 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.9075. Min Act: -0.1700
Data Index: 8067274 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.9075. Min Act: -0.1700
Data Index: 4517835 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.9075. Min Act: -0.1700
Data Index: 8285226 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.8450. Min Act: -0.1700
Data Index: 2301950 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.9075. Min Act: -0.1700
Data Index: 6077294 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.7825. Min Act: -0.1700
Data Index: 2434616 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.7825. Min Act: -0.1700
Data Index: 6558274 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.7825. Min Act: -0.1700
Data Index: 3540253 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.7825. Min Act: -0.1700
Data Index: 7629197 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5325. Min Range: -10.5325
Max Act: 9.7200. Min Act: -0.1700
Data Index: 8194662 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19