Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1296 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.4810. Min Act: -0.1700
Data Index: 7671890 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.3560. Min Act: -0.1700
Data Index: 1639015 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.2310. Min Act: -0.1700
Data Index: 5968891 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.1997. Min Act: -0.1700
Data Index: 812978 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.1372. Min Act: -0.1700
Data Index: 557401 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.0122. Min Act: -0.1700
Data Index: 3184859 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.9810. Min Act: -0.1700
Data Index: 2047234 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.9810. Min Act: -0.1700
Data Index: 5448517 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.9185. Min Act: -0.1700
Data Index: 4144045 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.8560. Min Act: -0.1700
Data Index: 2443285 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.8560. Min Act: -0.1700
Data Index: 620775 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.8560. Min Act: -0.1700
Data Index: 4578320 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.7935. Min Act: -0.1700
Data Index: 2566589 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.7310. Min Act: -0.1700
Data Index: 3327336 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.6997. Min Act: -0.1700
Data Index: 6717216 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.6997. Min Act: -0.1700
Data Index: 6473348 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.6685. Min Act: -0.1700
Data Index: 3748192 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.6372. Min Act: -0.1700
Data Index: 6313264 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.6372. Min Act: -0.1700
Data Index: 4144199 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.6372. Min Act: -0.1700
Data Index: 3445344 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19