Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.9470. Min Act: -0.1700
Data Index: 3807980 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.8845. Min Act: -0.1700
Data Index: 6168086 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.8532. Min Act: -0.1700
Data Index: 7144209 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.8845. Min Act: -0.1700
Data Index: 1825745 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.7907. Min Act: -0.1700
Data Index: 4388409 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.7907. Min Act: -0.1700
Data Index: 1321317 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.7595. Min Act: -0.1700
Data Index: 6477557 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.7282. Min Act: -0.1700
Data Index: 2063170 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.7282. Min Act: -0.1700
Data Index: 2949980 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.6970. Min Act: -0.1700
Data Index: 4988403 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.6657. Min Act: -0.1700
Data Index: 1906941 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.6657. Min Act: -0.1700
Data Index: 3258384 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.6657. Min Act: -0.1700
Data Index: 8380830 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.6345. Min Act: -0.1700
Data Index: 3969087 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.6032. Min Act: -0.1700
Data Index: 1782795 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.6032. Min Act: -0.1700
Data Index: 2314488 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.5720. Min Act: -0.1700
Data Index: 5585538 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.5407. Min Act: -0.1700
Data Index: 5820902 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.5407. Min Act: -0.1700
Data Index: 3076137 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9470. Min Range: -4.9470
Max Act: 4.5407. Min Act: -0.1700
Data Index: 4720472 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19