Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 811 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.4521. Min Act: -0.1700
Data Index: 1937420 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2959. Min Act: -0.1700
Data Index: 4035847 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2959. Min Act: -0.1700
Data Index: 5921718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2959. Min Act: -0.1700
Data Index: 1060660 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2959. Min Act: -0.1700
Data Index: 950962 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2646. Min Act: -0.1700
Data Index: 5188734 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2646. Min Act: -0.1700
Data Index: 1920809 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2334. Min Act: -0.1700
Data Index: 2636796 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2334. Min Act: -0.1700
Data Index: 7653482 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 4655377 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.2021. Min Act: -0.1700
Data Index: 1562443 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 2925006 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 6485059 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 779612 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 6036516 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1694
Data Index: 3099958 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 5158303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 8227304 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 5353853 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4521. Min Range: -4.4521
Max Act: 4.1709. Min Act: -0.1700
Data Index: 1995109 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19