Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.8897. Min Act: -0.1700
Data Index: 7670494 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.8272. Min Act: -0.1700
Data Index: 8774865 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.8272. Min Act: -0.1700
Data Index: 426397 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.5147. Min Act: -0.1700
Data Index: 5923019 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.5147. Min Act: -0.1700
Data Index: 1210405 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3897. Min Act: -0.1700
Data Index: 5570256 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3897. Min Act: -0.1700
Data Index: 3826960 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3272. Min Act: -0.1700
Data Index: 6524556 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3897. Min Act: -0.1700
Data Index: 2627320 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3272. Min Act: -0.1700
Data Index: 2095242 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.2647. Min Act: -0.1700
Data Index: 6193187 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3272. Min Act: -0.1700
Data Index: 5704738 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3272. Min Act: -0.1700
Data Index: 6862747 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3897. Min Act: -0.1700
Data Index: 4217947 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3897. Min Act: -0.1700
Data Index: 77824 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.3272. Min Act: -0.1700
Data Index: 1955602 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.2022. Min Act: -0.1700
Data Index: 3036481 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.2647. Min Act: -0.1700
Data Index: 1038304 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.2647. Min Act: -0.1700
Data Index: 5633856 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8897. Min Range: -9.8897
Max Act: 9.2647. Min Act: -0.1700
Data Index: 6471146 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19