Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2130. Min Range: -3.2130
Max Act: 3.2130. Min Act: -0.1700
Data Index: 7710032 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2130. Min Range: -3.2130
Max Act: 3.1343. Min Act: -0.1700
Data Index: 8514414 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2130. Min Range: -3.2130
Max Act: 3.0870. Min Act: -0.1700
Data Index: 1325380 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2130. Min Range: -3.2130
Max Act: 3.0712. Min Act: -0.1700
Data Index: 4505069 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2130. Min Range: -3.2130
Max Act: 3.0870. Min Act: -0.1700
Data Index: 5861602 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2130. Min Range: -3.2130
Max Act: 3.0555. Min Act: -0.1700
Data Index: 1124123 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2130. Min Range: -3.2130
Max Act: 3.0397. Min Act: -0.1700
Data Index: 4831195 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2130. Min Range: -3.2130
Max Act: 3.0239. Min Act: -0.1700
Data Index: 6189416 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9923. Min Act: -0.1700
Data Index: 1198980 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9607. Min Act: -0.1700
Data Index: 5052076 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9765. Min Act: -0.1700
Data Index: 5799924 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9607. Min Act: -0.1700
Data Index: 8555620 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9607. Min Act: -0.1700
Data Index: 4573827 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9448. Min Act: -0.1700
Data Index: 5847224 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9448. Min Act: -0.1700
Data Index: 4190108 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9607. Min Act: -0.1700
Data Index: 4047428 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9131. Min Act: -0.1700
Data Index: 5702673 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9290. Min Act: -0.1700
Data Index: 2796511 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.9131. Min Act: -0.1700
Data Index: 4538302 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2130. Min Range: -3.2130
Max Act: 2.8814. Min Act: -0.1700
Data Index: 998776 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19