Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.9202. Min Act: -0.1700
Data Index: 2412108 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.9515. Min Act: -0.1700
Data Index: 7014322 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.9202. Min Act: -0.1700
Data Index: 8650395 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8577. Min Act: -0.1700
Data Index: 7366903 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8577. Min Act: -0.1700
Data Index: 5330445 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8265. Min Act: -0.1700
Data Index: 7424431 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7952. Min Act: -0.1700
Data Index: 2163852 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7327. Min Act: -0.1700
Data Index: 6576057 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7640. Min Act: -0.1700
Data Index: 6838478 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7015. Min Act: -0.1700
Data Index: 5422043 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7015. Min Act: -0.1700
Data Index: 3634979 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6390. Min Act: -0.1700
Data Index: 1863763 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6390. Min Act: -0.1700
Data Index: 4761953 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6702. Min Act: -0.1700
Data Index: 1677945 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6390. Min Act: -0.1700
Data Index: 8526512 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6390. Min Act: -0.1700
Data Index: 2790433 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6390. Min Act: -0.1700
Data Index: 6870283 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6390. Min Act: -0.1700
Data Index: 3434015 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6390. Min Act: -0.1700
Data Index: 1859591 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6390. Min Act: -0.1700
Data Index: 7585987 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19