Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.8964. Min Act: -0.1700
Data Index: 8330165 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.9277. Min Act: -0.1700
Data Index: 1980765 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.8339. Min Act: -0.1700
Data Index: 7685691 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.8652. Min Act: -0.1700
Data Index: 771232 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.7714. Min Act: -0.1700
Data Index: 5859531 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.8027. Min Act: -0.1700
Data Index: 2008131 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.8339. Min Act: -0.1700
Data Index: 3700862 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.8027. Min Act: -0.1700
Data Index: 8255502 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.8027. Min Act: -0.1700
Data Index: 5937940 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.7402. Min Act: -0.1700
Data Index: 6062763 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.7402. Min Act: -0.1700
Data Index: 4491304 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.7089. Min Act: -0.1700
Data Index: 7678392 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.7089. Min Act: -0.1700
Data Index: 4134520 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.7089. Min Act: -0.1700
Data Index: 5978924 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.7089. Min Act: -0.1700
Data Index: 6723207 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.6464. Min Act: -0.1700
Data Index: 5954608 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.6464. Min Act: -0.1700
Data Index: 2103351 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.6464. Min Act: -0.1700
Data Index: 6057439 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.6777. Min Act: -0.1700
Data Index: 5107714 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9277. Min Range: -4.9277
Max Act: 4.6464. Min Act: -0.1700
Data Index: 2008129 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19