Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1203 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.8455. Min Act: -0.1700
Data Index: 512102 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.7340. Min Act: -0.1700
Data Index: 3630660 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.7020. Min Act: -0.1700
Data Index: 6287542 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6540. Min Act: -0.1700
Data Index: 715437 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6540. Min Act: -0.1700
Data Index: 4413123 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6540. Min Act: -0.1700
Data Index: 5576668 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6379. Min Act: -0.1700
Data Index: 2463727 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6379. Min Act: -0.1700
Data Index: 1723039 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6379. Min Act: -0.1700
Data Index: 8039613 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6219. Min Act: -0.1700
Data Index: 1707625 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6058. Min Act: -0.1700
Data Index: 2387967 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6058. Min Act: -0.1700
Data Index: 5581327 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.5897. Min Act: -0.1700
Data Index: 8598880 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6058. Min Act: -0.1700
Data Index: 4006349 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6058. Min Act: -0.1700
Data Index: 185049 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.6058. Min Act: -0.1700
Data Index: 5010822 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.5897. Min Act: -0.1700
Data Index: 4249716 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.5897. Min Act: -0.1700
Data Index: 8773209 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.5897. Min Act: -0.1700
Data Index: 1050615 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8455. Min Range: -2.8455
Max Act: 2.5574. Min Act: -0.1700
Data Index: 4945196 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19