Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1617 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.2749. Min Act: -0.1700
Data Index: 8668287 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.1812. Min Act: -0.1700
Data Index: 8550454 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.0874. Min Act: -0.1700
Data Index: 2911834 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.0874. Min Act: -0.1700
Data Index: 4677423 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.1187. Min Act: -0.1700
Data Index: 3676286 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.0562. Min Act: -0.1700
Data Index: 7228095 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.0874. Min Act: -0.1700
Data Index: 7228094 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.0249. Min Act: -0.1700
Data Index: 3070665 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2749. Min Range: -5.2749
Max Act: 5.0249. Min Act: -0.1700
Data Index: 7178830 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.9937. Min Act: -0.1700
Data Index: 7467104 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.9937. Min Act: -0.1700
Data Index: 2506810 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.9312. Min Act: -0.1700
Data Index: 3973982 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.9312. Min Act: -0.1700
Data Index: 8152868 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.9312. Min Act: -0.1700
Data Index: 981869 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.9312. Min Act: -0.1700
Data Index: 4065282 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.8999. Min Act: -0.1700
Data Index: 6272909 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.8999. Min Act: -0.1700
Data Index: 5223635 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.8687. Min Act: -0.1700
Data Index: 3270139 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.8687. Min Act: -0.1700
Data Index: 6818619 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2749. Min Range: -5.2749
Max Act: 4.8374. Min Act: -0.1700
Data Index: 3070269 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19