Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.7241. Min Act: -0.1700
Data Index: 5029507 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.5366. Min Act: -0.1700
Data Index: 3030943 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.5366. Min Act: -0.1700
Data Index: 202472 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.4741. Min Act: -0.1700
Data Index: 1974595 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.4116. Min Act: -0.1700
Data Index: 8791751 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.4116. Min Act: -0.1700
Data Index: 6597464 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.4428. Min Act: -0.1700
Data Index: 6257937 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.4428. Min Act: -0.1700
Data Index: 7415248 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.3803. Min Act: -0.1700
Data Index: 7948318 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.4116. Min Act: -0.1700
Data Index: 3476295 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.3491. Min Act: -0.1700
Data Index: 1667095 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.3803. Min Act: -0.1700
Data Index: 2726182 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.3803. Min Act: -0.1700
Data Index: 317034 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.3178. Min Act: -0.1700
Data Index: 2240855 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.2866. Min Act: -0.1700
Data Index: 104307 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.2553. Min Act: -0.1700
Data Index: 864363 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.2241. Min Act: -0.1700
Data Index: 427920 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.2553. Min Act: -0.1700
Data Index: 5023034 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.2241. Min Act: -0.1700
Data Index: 8365981 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7241. Min Range: -7.7241
Max Act: 7.1928. Min Act: -0.1700
Data Index: 6783661 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19