Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3277 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.3223. Min Act: -0.1700
Data Index: 4398761 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.1973. Min Act: -0.1700
Data Index: 4585242 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.1661. Min Act: -0.1700
Data Index: 1887800 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.1348. Min Act: -0.1700
Data Index: 4847724 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.1348. Min Act: -0.1700
Data Index: 5744036 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.1348. Min Act: -0.1700
Data Index: 4663141 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.1036. Min Act: -0.1700
Data Index: 8590652 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.1036. Min Act: -0.1700
Data Index: 2370376 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.1036. Min Act: -0.1700
Data Index: 5066641 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0098. Min Act: -0.1700
Data Index: 8174672 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0411. Min Act: -0.1700
Data Index: 480313 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0723. Min Act: -0.1700
Data Index: 577250 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0098. Min Act: -0.1700
Data Index: 3911431 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0098. Min Act: -0.1700
Data Index: 7361489 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0098. Min Act: -0.1700
Data Index: 4575089 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0098. Min Act: -0.1700
Data Index: 1865544 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0098. Min Act: -0.1700
Data Index: 5913147 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0098. Min Act: -0.1700
Data Index: 3444192 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0411. Min Act: -0.1700
Data Index: 6764036 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3223. Min Range: -5.3223
Max Act: 5.0098. Min Act: -0.1700
Data Index: 1555676 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19