Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4913 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.8339. Min Act: -0.1700
Data Index: 8369623 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.7401. Min Act: -0.1700
Data Index: 8440134 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.6776. Min Act: -0.1700
Data Index: 7241977 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.6464. Min Act: -0.1700
Data Index: 7111346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.6464. Min Act: -0.1700
Data Index: 6242678 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.6151. Min Act: -0.1700
Data Index: 7414151 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.6151. Min Act: -0.1700
Data Index: 4925426 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.6151. Min Act: -0.1700
Data Index: 2067771 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5526. Min Act: -0.1700
Data Index: 1004185 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5839. Min Act: -0.1700
Data Index: 5053560 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5839. Min Act: -0.1700
Data Index: 591076 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5839. Min Act: -0.1700
Data Index: 202425 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5839. Min Act: -0.1700
Data Index: 2653899 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5839. Min Act: -0.1700
Data Index: 2479615 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5526. Min Act: -0.1700
Data Index: 4473565 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5526. Min Act: -0.1700
Data Index: 7099566 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5526. Min Act: -0.1700
Data Index: 6826047 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5214. Min Act: -0.1700
Data Index: 1652746 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5526. Min Act: -0.1700
Data Index: 5940933 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8339. Min Range: -4.8339
Max Act: 4.5526. Min Act: -0.1700
Data Index: 5765631 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19