Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2101 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.3885. Min Act: -0.1700
Data Index: 6862711 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.1072. Min Act: -0.1700
Data Index: 7532541 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.0760. Min Act: -0.1700
Data Index: 7394340 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.0447. Min Act: -0.1700
Data Index: 8108297 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.0760. Min Act: -0.1700
Data Index: 8231004 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.0760. Min Act: -0.1700
Data Index: 6893389 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.0760. Min Act: -0.1700
Data Index: 8577314 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.0447. Min Act: -0.1700
Data Index: 79924 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3885. Min Range: -6.3885
Max Act: 6.0135. Min Act: -0.1700
Data Index: 650759 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.9822. Min Act: -0.1700
Data Index: 1318864 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.9822. Min Act: -0.1700
Data Index: 3218071 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.9197. Min Act: -0.1700
Data Index: 1758037 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.9510. Min Act: -0.1700
Data Index: 2360289 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.9510. Min Act: -0.1700
Data Index: 867924 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.9197. Min Act: -0.1700
Data Index: 4596053 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.9197. Min Act: -0.1700
Data Index: 4332491 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.8572. Min Act: -0.1700
Data Index: 4211317 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.8885. Min Act: -0.1700
Data Index: 6947713 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.8572. Min Act: -0.1700
Data Index: 6297706 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3885. Min Range: -6.3885
Max Act: 5.8572. Min Act: -0.1700
Data Index: 2249448 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19