Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.9501. Min Act: -0.1700
Data Index: 7578535 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.8876. Min Act: -0.1700
Data Index: 1333357 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.7937. Min Act: -0.1700
Data Index: 1634420 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.7937. Min Act: -0.1700
Data Index: 2351683 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.8250. Min Act: -0.1700
Data Index: 7172943 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.7937. Min Act: -0.1700
Data Index: 4025123 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.7625. Min Act: -0.1700
Data Index: 8752438 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.7937. Min Act: -0.1700
Data Index: 1201660 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.7312. Min Act: -0.1700
Data Index: 8584077 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.7625. Min Act: -0.1700
Data Index: 332614 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.7625. Min Act: -0.1700
Data Index: 3258932 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6999. Min Act: -0.1700
Data Index: 3777426 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6999. Min Act: -0.1700
Data Index: 280417 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6999. Min Act: -0.1700
Data Index: 8580146 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6999. Min Act: -0.1700
Data Index: 3662641 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6373. Min Act: -0.1700
Data Index: 3987574 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6373. Min Act: -0.1700
Data Index: 1209515 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6373. Min Act: -0.1700
Data Index: 3870891 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6060. Min Act: -0.1700
Data Index: 7464797 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9501. Min Range: -3.9501
Max Act: 3.6373. Min Act: -0.1700
Data Index: 157975 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19