Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0477. Min Range: -7.0477
Max Act: 7.0165. Min Act: -0.1700
Data Index: 4562956 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0477. Min Range: -7.0477
Max Act: 7.0477. Min Act: -0.1700
Data Index: 5120384 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.8290. Min Act: -0.1700
Data Index: 5493962 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.7977. Min Act: -0.1700
Data Index: 4867761 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.7352. Min Act: -0.1700
Data Index: 5653727 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.7040. Min Act: -0.1700
Data Index: 7277892 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.6727. Min Act: -0.1700
Data Index: 6098761 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.5790. Min Act: -0.1700
Data Index: 1639026 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.5790. Min Act: -0.1700
Data Index: 3200926 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4540. Min Act: -0.1700
Data Index: 3198994 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4852. Min Act: -0.1700
Data Index: 5933672 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4540. Min Act: -0.1700
Data Index: 7461624 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4227. Min Act: -0.1700
Data Index: 1946989 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4540. Min Act: -0.1700
Data Index: 7710428 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4227. Min Act: -0.1700
Data Index: 4882145 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4227. Min Act: -0.1700
Data Index: 3283278 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4227. Min Act: -0.1700
Data Index: 6045520 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4227. Min Act: -0.1700
Data Index: 1498468 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4227. Min Act: -0.1700
Data Index: 1312759 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0477. Min Range: -7.0477
Max Act: 6.4540. Min Act: -0.1700
Data Index: 1269366 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19