Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5039 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.7958. Min Act: -0.1700
Data Index: 2241999 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.4520. Min Act: -0.1700
Data Index: 1107180 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.4520. Min Act: -0.1700
Data Index: 2242000 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.4208. Min Act: -0.1700
Data Index: 5744687 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.2645. Min Act: -0.1700
Data Index: 7391805 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.1395. Min Act: -0.1700
Data Index: 7603257 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.1708. Min Act: -0.1700
Data Index: 2627259 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.1083. Min Act: -0.1700
Data Index: 1344686 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.0770. Min Act: -0.1700
Data Index: 3714534 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.0458. Min Act: -0.1700
Data Index: 5518444 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.0145. Min Act: -0.1700
Data Index: 2665791 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.0145. Min Act: -0.1700
Data Index: 7714401 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7958. Min Range: -6.7958
Max Act: 6.0145. Min Act: -0.1700
Data Index: 1852138 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7958. Min Range: -6.7958
Max Act: 5.9833. Min Act: -0.1700
Data Index: 6818795 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7958. Min Range: -6.7958
Max Act: 5.9520. Min Act: -0.1700
Data Index: 3125910 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7958. Min Range: -6.7958
Max Act: 5.9520. Min Act: -0.1700
Data Index: 8090386 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7958. Min Range: -6.7958
Max Act: 5.9208. Min Act: -0.1700
Data Index: 6666313 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7958. Min Range: -6.7958
Max Act: 5.8895. Min Act: -0.1700
Data Index: 4584683 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7958. Min Range: -6.7958
Max Act: 5.8895. Min Act: -0.1700
Data Index: 359548 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7958. Min Range: -6.7958
Max Act: 5.8583. Min Act: -0.1700
Data Index: 8561023 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19