Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2522. Min Range: -7.2522
Max Act: 7.2522. Min Act: -0.1700
Data Index: 2624778 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.9709. Min Act: -0.1700
Data Index: 7539513 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.9084. Min Act: -0.1700
Data Index: 5386648 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.8459. Min Act: -0.1700
Data Index: 3084043 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.8459. Min Act: -0.1700
Data Index: 3918441 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.8147. Min Act: -0.1700
Data Index: 100353 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.7834. Min Act: -0.1700
Data Index: 3265507 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.6584. Min Act: -0.1700
Data Index: 8257577 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.7209. Min Act: -0.1700
Data Index: 2787253 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.6584. Min Act: -0.1700
Data Index: 7851678 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.6272. Min Act: -0.1700
Data Index: 3201486 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.5959. Min Act: -0.1700
Data Index: 7317610 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.5647. Min Act: -0.1700
Data Index: 1500584 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.5334. Min Act: -0.1700
Data Index: 1328397 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.5334. Min Act: -0.1700
Data Index: 5829030 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.5022. Min Act: -0.1700
Data Index: 1447989 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.4709. Min Act: -0.1700
Data Index: 1803535 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.4397. Min Act: -0.1700
Data Index: 32859 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.5022. Min Act: -0.1700
Data Index: 6800859 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2522. Min Range: -7.2522
Max Act: 6.4709. Min Act: -0.1700
Data Index: 5583858 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19