Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2337 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.8016. Min Act: -0.1700
Data Index: 5778615 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.5204. Min Act: -0.1700
Data Index: 783810 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.4266. Min Act: -0.1700
Data Index: 8045737 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3641. Min Act: -0.1700
Data Index: 8068889 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3641. Min Act: -0.1700
Data Index: 8144900 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3329. Min Act: -0.1700
Data Index: 7514897 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3329. Min Act: -0.1700
Data Index: 5311951 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3641. Min Act: -0.1700
Data Index: 2693732 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3329. Min Act: -0.1700
Data Index: 2456045 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3016. Min Act: -0.1700
Data Index: 1056663 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3329. Min Act: -0.1700
Data Index: 2154692 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3329. Min Act: -0.1700
Data Index: 6029447 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3016. Min Act: -0.1700
Data Index: 3990110 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3016. Min Act: -0.1700
Data Index: 4889041 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3329. Min Act: -0.1700
Data Index: 3111130 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.3016. Min Act: -0.1700
Data Index: 5031665 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.2704. Min Act: -0.1700
Data Index: 3134325 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.2704. Min Act: -0.1700
Data Index: 1561159 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.2391. Min Act: -0.1700
Data Index: 2979324 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8016. Min Range: -5.8016
Max Act: 5.2391. Min Act: -0.1700
Data Index: 6382809 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19