Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.4487. Min Act: -0.1700
Data Index: 6374085 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3862. Min Act: -0.1700
Data Index: 2285061 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3862. Min Act: -0.1700
Data Index: 1411065 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.3862. Min Act: -0.1700
Data Index: 6628243 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2612. Min Act: -0.1700
Data Index: 5046180 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.2299. Min Act: -0.1700
Data Index: 1250604 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.1674. Min Act: -0.1700
Data Index: 1954883 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.1674. Min Act: -0.1700
Data Index: 477354 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.1674. Min Act: -0.1700
Data Index: 6969279 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.1362. Min Act: -0.1700
Data Index: 5981862 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.1049. Min Act: -0.1700
Data Index: 2820460 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.0737. Min Act: -0.1700
Data Index: 8073152 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.1049. Min Act: -0.1700
Data Index: 6068669 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.0737. Min Act: -0.1700
Data Index: 1990260 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.0737. Min Act: -0.1700
Data Index: 6228553 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.0737. Min Act: -0.1700
Data Index: 7023774 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.0424. Min Act: -0.1700
Data Index: 6604511 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.0424. Min Act: -0.1700
Data Index: 6353838 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.0424. Min Act: -0.1700
Data Index: 119296 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4487. Min Range: -4.4487
Max Act: 4.0111. Min Act: -0.1700
Data Index: 5523172 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19