Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2203 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.9301. Min Act: -0.1700
Data Index: 1774096 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.8364. Min Act: -0.1700
Data Index: 5572750 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.7739. Min Act: -0.1700
Data Index: 6807819 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.6176. Min Act: -0.1700
Data Index: 4715175 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.5551. Min Act: -0.1700
Data Index: 3678587 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.5551. Min Act: -0.1700
Data Index: 587091 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.5864. Min Act: -0.1700
Data Index: 2072226 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.5864. Min Act: -0.1700
Data Index: 7520570 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.6176. Min Act: -0.1700
Data Index: 2012822 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.5551. Min Act: -0.1700
Data Index: 101174 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.5239. Min Act: -0.1700
Data Index: 5509879 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.5239. Min Act: -0.1700
Data Index: 2012820 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.4926. Min Act: -0.1700
Data Index: 2548769 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.5239. Min Act: -0.1700
Data Index: 4905767 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.4614. Min Act: -0.1700
Data Index: 1599327 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.4614. Min Act: -0.1700
Data Index: 1996263 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.3989. Min Act: -0.1700
Data Index: 4324185 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.4614. Min Act: -0.1700
Data Index: 39841 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.4301. Min Act: -0.1700
Data Index: 4068197 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9301. Min Range: -5.9301
Max Act: 5.4301. Min Act: -0.1700
Data Index: 534806 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19