Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4469 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.7044. Min Act: -0.1700
Data Index: 4826188 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.6107. Min Act: -0.1700
Data Index: 6329641 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.5482. Min Act: -0.1700
Data Index: 3505200 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.4857. Min Act: -0.1700
Data Index: 3543587 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.4544. Min Act: -0.1700
Data Index: 1323385 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.4544. Min Act: -0.1700
Data Index: 5395199 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.4544. Min Act: -0.1700
Data Index: 8569869 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.4544. Min Act: -0.1700
Data Index: 5570541 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3919. Min Act: -0.1700
Data Index: 5404561 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.4232. Min Act: -0.1700
Data Index: 38528 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3919. Min Act: -0.1700
Data Index: 363884 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3607. Min Act: -0.1700
Data Index: 4171601 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 7993673 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3607. Min Act: -0.1700
Data Index: 4464328 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3607. Min Act: -0.1700
Data Index: 6249782 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 6046262 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 6468249 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 3752968 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 3303152 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 1392888 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19