Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1973 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3343. Min Range: -8.3343
Max Act: 8.3343. Min Act: -0.1700
Data Index: 8533894 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.8968. Min Act: -0.1700
Data Index: 8125336 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.8343. Min Act: -0.1700
Data Index: 4476077 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.7718. Min Act: -0.1700
Data Index: 4546443 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.7718. Min Act: -0.1700
Data Index: 5166468 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.7718. Min Act: -0.1700
Data Index: 6568708 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.7718. Min Act: -0.1700
Data Index: 3048227 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.7718. Min Act: -0.1700
Data Index: 7570070 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.7718. Min Act: -0.1700
Data Index: 2445691 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.7093. Min Act: -0.1700
Data Index: 6164771 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.7093. Min Act: -0.1700
Data Index: 4583524 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.6468. Min Act: -0.1700
Data Index: 5073367 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.6155. Min Act: -0.1700
Data Index: 7610428 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.6155. Min Act: -0.1700
Data Index: 613746 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.6155. Min Act: -0.1700
Data Index: 3840262 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.6155. Min Act: -0.1700
Data Index: 6615387 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.5530. Min Act: -0.1700
Data Index: 4934453 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.5218. Min Act: -0.1700
Data Index: 2511206 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.4905. Min Act: -0.1700
Data Index: 4308221 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3343. Min Range: -8.3343
Max Act: 7.5218. Min Act: -0.1700
Data Index: 6916357 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19