Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.7360. Min Act: -0.1700
Data Index: 5949806 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.7047. Min Act: -0.1700
Data Index: 8293706 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.6109. Min Act: -0.1700
Data Index: 5531413 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.6109. Min Act: -0.1700
Data Index: 5741207 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.6109. Min Act: -0.1700
Data Index: 4756623 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.5796. Min Act: -0.1700
Data Index: 1153005 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.5639. Min Act: -0.1700
Data Index: 110362 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.5326. Min Act: -0.1700
Data Index: 4112151 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4856. Min Act: -0.1700
Data Index: 5684401 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4856. Min Act: -0.1700
Data Index: 587554 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4699. Min Act: -0.1700
Data Index: 5028711 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4856. Min Act: -0.1700
Data Index: 2682923 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4543. Min Act: -0.1700
Data Index: 5140531 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4543. Min Act: -0.1700
Data Index: 8233068 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4386. Min Act: -0.1700
Data Index: 2547117 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4543. Min Act: -0.1700
Data Index: 4118418 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4386. Min Act: -0.1700
Data Index: 1663106 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4386. Min Act: -0.1700
Data Index: 2105006 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4386. Min Act: -0.1700
Data Index: 8664893 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7360. Min Range: -3.7360
Max Act: 3.4073. Min Act: -0.1700
Data Index: 173686 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19