Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 974 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6880. Min Range: -6.6880
Max Act: 6.6880. Min Act: -0.1700
Data Index: 7869202 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6880. Min Range: -6.6880
Max Act: 6.3130. Min Act: -0.1700
Data Index: 7349455 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6880. Min Range: -6.6880
Max Act: 6.3442. Min Act: -0.1700
Data Index: 4245695 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6880. Min Range: -6.6880
Max Act: 6.1567. Min Act: -0.1700
Data Index: 2525293 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6880. Min Range: -6.6880
Max Act: 6.0942. Min Act: -0.1700
Data Index: 5250725 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.9692. Min Act: -0.1700
Data Index: 2221441 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.9692. Min Act: -0.1700
Data Index: 2650226 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.9692. Min Act: -0.1700
Data Index: 2465213 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.8755. Min Act: -0.1700
Data Index: 671073 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.8442. Min Act: -0.1700
Data Index: 2985558 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.8442. Min Act: -0.1700
Data Index: 7109770 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.8130. Min Act: -0.1700
Data Index: 7475081 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.8442. Min Act: -0.1700
Data Index: 6786111 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.7817. Min Act: -0.1700
Data Index: 3550692 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.7817. Min Act: -0.1700
Data Index: 6786112 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.7817. Min Act: -0.1700
Data Index: 3809218 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.8130. Min Act: -0.1700
Data Index: 3765474 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.7817. Min Act: -0.1700
Data Index: 8355600 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.7505. Min Act: -0.1700
Data Index: 7109769 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6880. Min Range: -6.6880
Max Act: 5.7817. Min Act: -0.1700
Data Index: 4641995 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19