Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.4704. Min Act: -0.1700
Data Index: 3067567 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.4079. Min Act: -0.1700
Data Index: 7392855 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.3767. Min Act: -0.1700
Data Index: 8811562 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.3454. Min Act: -0.1700
Data Index: 2479972 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.3454. Min Act: -0.1700
Data Index: 1092199 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.3142. Min Act: -0.1700
Data Index: 3397091 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2829. Min Act: -0.1700
Data Index: 194578 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2829. Min Act: -0.1700
Data Index: 5457265 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2517. Min Act: -0.1700
Data Index: 5239474 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2517. Min Act: -0.1700
Data Index: 806462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2517. Min Act: -0.1700
Data Index: 818015 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2204. Min Act: -0.1700
Data Index: 3037285 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.1892. Min Act: -0.1700
Data Index: 1561245 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2204. Min Act: -0.1700
Data Index: 6941937 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2204. Min Act: -0.1700
Data Index: 6589900 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.2204. Min Act: -0.1700
Data Index: 616515 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.1892. Min Act: -0.1700
Data Index: 4074015 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.1892. Min Act: -0.1700
Data Index: 8689576 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.1579. Min Act: -0.1700
Data Index: 3628968 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4704. Min Range: -4.4704
Max Act: 4.1579. Min Act: -0.1700
Data Index: 6442260 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19