Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1689. Min Range: -6.1689
Max Act: 6.1689. Min Act: -0.1700
Data Index: 822431 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.9814. Min Act: -0.1700
Data Index: 7526882 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.9189. Min Act: -0.1700
Data Index: 7526873 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.5439. Min Act: -0.1700
Data Index: 7526877 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.4814. Min Act: -0.1700
Data Index: 7526886 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.5127. Min Act: -0.1700
Data Index: 1208477 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.4502. Min Act: -0.1700
Data Index: 7551382 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.4502. Min Act: -0.1700
Data Index: 3695809 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.4189. Min Act: -0.1700
Data Index: 380467 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.4189. Min Act: -0.1700
Data Index: 2700332 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.4189. Min Act: -0.1700
Data Index: 1339018 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.3564. Min Act: -0.1700
Data Index: 4934555 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.3252. Min Act: -0.1700
Data Index: 7526869 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.3252. Min Act: -0.1700
Data Index: 6661091 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.2314. Min Act: -0.1700
Data Index: 5779235 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.2002. Min Act: -0.1700
Data Index: 688348 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.2002. Min Act: -0.1700
Data Index: 2511990 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.2002. Min Act: -0.1700
Data Index: 2869961 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.2002. Min Act: -0.1700
Data Index: 1351365 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1689. Min Range: -6.1689
Max Act: 5.1689. Min Act: -0.1698
Data Index: 6052050 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19