Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 336 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.9459. Min Act: -0.1686
Data Index: 2832277 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.9289. Min Act: -0.1698
Data Index: 5375348 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.9119. Min Act: -0.1693
Data Index: 6015429 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.9119. Min Act: -0.1697
Data Index: 1943277 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8949. Min Act: -0.1628
Data Index: 6582497 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8949. Min Act: -0.1687
Data Index: 4598624 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8607. Min Act: -0.1700
Data Index: 8808485 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8436. Min Act: -0.1694
Data Index: 6305516 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8264. Min Act: -0.1698
Data Index: 6108523 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8264. Min Act: -0.1700
Data Index: 4102118 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8092. Min Act: -0.1700
Data Index: 7153522 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8264. Min Act: -0.1700
Data Index: 4044775 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8264. Min Act: -0.1624
Data Index: 443386 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8264. Min Act: -0.1658
Data Index: 3517020 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8264. Min Act: -0.1698
Data Index: 1303626 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8092. Min Act: -0.1700
Data Index: 5837662 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.7920. Min Act: -0.1700
Data Index: 7758724 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8092. Min Act: -0.1679
Data Index: 7610157 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.7920. Min Act: -0.1700
Data Index: 2413436 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9459. Min Range: -1.9459
Max Act: 1.8092. Min Act: -0.1700
Data Index: 2323377 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19