Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.3717. Min Act: -0.1700
Data Index: 4667047 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.3717. Min Act: -0.1700
Data Index: 3838971 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.2932. Min Act: -0.1700
Data Index: 427843 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.2461. Min Act: -0.1700
Data Index: 1837248 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1360. Min Act: -0.1700
Data Index: 2763000 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1360. Min Act: -0.1700
Data Index: 4442629 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1360. Min Act: -0.1700
Data Index: 6863004 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1360. Min Act: -0.1700
Data Index: 3626926 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1203. Min Act: -0.1700
Data Index: 609536 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1045. Min Act: -0.1700
Data Index: 1801460 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1045. Min Act: -0.1700
Data Index: 3606763 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1045. Min Act: -0.1700
Data Index: 6625361 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1045. Min Act: -0.1700
Data Index: 8602584 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1203. Min Act: -0.1700
Data Index: 5532909 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.0730. Min Act: -0.1700
Data Index: 3179946 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.1045. Min Act: -0.1700
Data Index: 4794493 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.0887. Min Act: -0.1700
Data Index: 6116784 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.0730. Min Act: -0.1700
Data Index: 7461171 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.0730. Min Act: -0.1700
Data Index: 4207902 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3717. Min Range: -3.3717
Max Act: 3.0887. Min Act: -0.1700
Data Index: 2762999 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19