Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.7947. Min Act: -0.1700
Data Index: 3313994 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.7322. Min Act: -0.1700
Data Index: 3879066 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.7010. Min Act: -0.1700
Data Index: 2938132 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.5135. Min Act: -0.1700
Data Index: 5302908 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.5760. Min Act: -0.1700
Data Index: 8316443 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.6072. Min Act: -0.1700
Data Index: 3976084 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.6072. Min Act: -0.1700
Data Index: 1219116 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.5760. Min Act: -0.1700
Data Index: 5763354 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.5760. Min Act: -0.1700
Data Index: 8492272 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.5760. Min Act: -0.1700
Data Index: 5331931 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.5135. Min Act: -0.1700
Data Index: 2350168 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.4822. Min Act: -0.1700
Data Index: 4244318 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.4822. Min Act: -0.1700
Data Index: 5747928 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.5447. Min Act: -0.1700
Data Index: 7286866 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.4510. Min Act: -0.1700
Data Index: 1205779 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.5135. Min Act: -0.1700
Data Index: 5747926 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.4197. Min Act: -0.1700
Data Index: 6319206 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.4510. Min Act: -0.1700
Data Index: 3464294 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.4822. Min Act: -0.1700
Data Index: 8445979 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7947. Min Range: -7.7947
Max Act: 7.4510. Min Act: -0.1700
Data Index: 6435819 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19