Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.8236. Min Act: -0.1700
Data Index: 1021566 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.5111. Min Act: -0.1700
Data Index: 4904737 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.5111. Min Act: -0.1700
Data Index: 2682911 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.4486. Min Act: -0.1700
Data Index: 1624415 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.4486. Min Act: -0.1700
Data Index: 3253190 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.4486. Min Act: -0.1700
Data Index: 7149805 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.4174. Min Act: -0.1700
Data Index: 8055318 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3861. Min Act: -0.1700
Data Index: 5537745 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3861. Min Act: -0.1700
Data Index: 406140 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3549. Min Act: -0.1700
Data Index: 7435861 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3549. Min Act: -0.1700
Data Index: 6295346 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3236. Min Act: -0.1700
Data Index: 1024146 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3549. Min Act: -0.1700
Data Index: 113806 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3236. Min Act: -0.1700
Data Index: 1212353 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3236. Min Act: -0.1700
Data Index: 7798423 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.3236. Min Act: -0.1700
Data Index: 4637852 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.2924. Min Act: -0.1700
Data Index: 5466617 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.2924. Min Act: -0.1700
Data Index: 2682775 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.2611. Min Act: -0.1700
Data Index: 623773 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8236. Min Range: -5.8236
Max Act: 5.2611. Min Act: -0.1700
Data Index: 4836416 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19