Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.1016. Min Act: -0.1700
Data Index: 8126686 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.1329. Min Act: -0.1700
Data Index: 1158172 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.1016. Min Act: -0.1700
Data Index: 3411394 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.1016. Min Act: -0.1700
Data Index: 4584860 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.1016. Min Act: -0.1700
Data Index: 7018671 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.0704. Min Act: -0.1700
Data Index: 6255156 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.0704. Min Act: -0.1700
Data Index: 7603732 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.0079. Min Act: -0.1700
Data Index: 3538844 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.0391. Min Act: -0.1700
Data Index: 533449 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1329. Min Range: -4.1329
Max Act: 4.0079. Min Act: -0.1700
Data Index: 3966 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 2361222 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 2081855 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 7754104 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9453. Min Act: -0.1700
Data Index: 4324110 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 3252863 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 7153180 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 3798508 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 5911289 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 5366717 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1329. Min Range: -4.1329
Max Act: 3.9766. Min Act: -0.1700
Data Index: 2735610 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19