Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2921. Min Range: -5.2921
Max Act: 5.2921. Min Act: -0.1700
Data Index: 1701672 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2921. Min Range: -5.2921
Max Act: 5.0733. Min Act: -0.1700
Data Index: 1823279 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.9796. Min Act: -0.1700
Data Index: 6312021 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.9796. Min Act: -0.1700
Data Index: 8565513 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.9483. Min Act: -0.1700
Data Index: 3684650 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.9483. Min Act: -0.1700
Data Index: 2677209 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.9483. Min Act: -0.1700
Data Index: 2787217 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.9171. Min Act: -0.1700
Data Index: 4259138 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.8858. Min Act: -0.1700
Data Index: 6560565 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.8858. Min Act: -0.1700
Data Index: 7752876 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.8546. Min Act: -0.1700
Data Index: 4030767 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.8233. Min Act: -0.1700
Data Index: 3386356 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.8233. Min Act: -0.1700
Data Index: 6796969 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.8233. Min Act: -0.1700
Data Index: 6863919 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.7921. Min Act: -0.1700
Data Index: 7865814 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.7921. Min Act: -0.1700
Data Index: 7865801 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.8233. Min Act: -0.1700
Data Index: 260568 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.7921. Min Act: -0.1700
Data Index: 7351311 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.7608. Min Act: -0.1700
Data Index: 4387082 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2921. Min Range: -5.2921
Max Act: 4.7608. Min Act: -0.1700
Data Index: 1991144 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19