Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6958. Min Range: -8.6958
Max Act: 8.6958. Min Act: -0.1700
Data Index: 4888337 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6958. Min Range: -8.6958
Max Act: 8.1958. Min Act: -0.1700
Data Index: 6517538 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6958. Min Range: -8.6958
Max Act: 8.1645. Min Act: -0.1700
Data Index: 134379 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6958. Min Range: -8.6958
Max Act: 8.0083. Min Act: -0.1700
Data Index: 7797078 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.9770. Min Act: -0.1700
Data Index: 3065412 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.9458. Min Act: -0.1700
Data Index: 3729532 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.9145. Min Act: -0.1700
Data Index: 6665433 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.9145. Min Act: -0.1700
Data Index: 3901412 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 8355532 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.8520. Min Act: -0.1700
Data Index: 8443342 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 3081935 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 1491454 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 4859284 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.7895. Min Act: -0.1700
Data Index: 8378782 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.7895. Min Act: -0.1700
Data Index: 8043430 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.7270. Min Act: -0.1700
Data Index: 6136027 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.7270. Min Act: -0.1700
Data Index: 7924556 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.7270. Min Act: -0.1700
Data Index: 1337661 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.6958. Min Act: -0.1700
Data Index: 4523977 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6958. Min Range: -8.6958
Max Act: 7.6958. Min Act: -0.1700
Data Index: 264372 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19