Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5058 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.7849. Min Act: -0.1700
Data Index: 7622599 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.7537. Min Act: -0.1700
Data Index: 1328484 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.7849. Min Act: -0.1700
Data Index: 3827349 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.7537. Min Act: -0.1700
Data Index: 6755620 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.6912. Min Act: -0.1700
Data Index: 3356544 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.6599. Min Act: -0.1700
Data Index: 2620405 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5662. Min Act: -0.1700
Data Index: 6239551 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5662. Min Act: -0.1700
Data Index: 6462359 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5662. Min Act: -0.1700
Data Index: 2311144 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5662. Min Act: -0.1700
Data Index: 5525188 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5349. Min Act: -0.1700
Data Index: 8387330 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5662. Min Act: -0.1700
Data Index: 8323693 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5349. Min Act: -0.1700
Data Index: 5027547 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5349. Min Act: -0.1700
Data Index: 7561975 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5037. Min Act: -0.1700
Data Index: 8036321 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5037. Min Act: -0.1700
Data Index: 1690863 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5037. Min Act: -0.1700
Data Index: 4814455 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.5037. Min Act: -0.1700
Data Index: 7536084 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.4724. Min Act: -0.1700
Data Index: 451319 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7849. Min Range: -4.7849
Max Act: 4.4724. Min Act: -0.1700
Data Index: 3938884 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19