Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1419 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.6093. Min Act: -0.1700
Data Index: 5020013 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.5468. Min Act: -0.1700
Data Index: 6362405 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.5468. Min Act: -0.1700
Data Index: 2040184 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.4843. Min Act: -0.1700
Data Index: 6383779 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.3906. Min Act: -0.1700
Data Index: 2752054 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.2968. Min Act: -0.1700
Data Index: 7588994 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.2968. Min Act: -0.1700
Data Index: 4906259 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.2968. Min Act: -0.1700
Data Index: 8517501 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.2968. Min Act: -0.1700
Data Index: 5373922 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.2031. Min Act: -0.1700
Data Index: 3627922 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.2656. Min Act: -0.1700
Data Index: 987986 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.2343. Min Act: -0.1700
Data Index: 1463381 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.1718. Min Act: -0.1700
Data Index: 4410685 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.1093. Min Act: -0.1700
Data Index: 8425513 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.1718. Min Act: -0.1700
Data Index: 1485981 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.1093. Min Act: -0.1700
Data Index: 2337096 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.1406. Min Act: -0.1700
Data Index: 5373917 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.1093. Min Act: -0.1700
Data Index: 4849558 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.0468. Min Act: -0.1700
Data Index: 4161062 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6093. Min Range: -7.6093
Max Act: 7.1093. Min Act: -0.1700
Data Index: 1463368 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19