Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 949 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.1599. Min Act: -0.1700
Data Index: 4551011 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.1599. Min Act: -0.1700
Data Index: 453025 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.1599. Min Act: -0.1700
Data Index: 5192728 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.1286. Min Act: -0.1700
Data Index: 2353151 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0974. Min Act: -0.1700
Data Index: 4526374 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0974. Min Act: -0.1700
Data Index: 2712827 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0974. Min Act: -0.1700
Data Index: 6649939 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0661. Min Act: -0.1700
Data Index: 2801727 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0974. Min Act: -0.1700
Data Index: 3312201 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0348. Min Act: -0.1700
Data Index: 854194 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0036. Min Act: -0.1700
Data Index: 8393915 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0036. Min Act: -0.1700
Data Index: 3650591 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0036. Min Act: -0.1700
Data Index: 624518 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0036. Min Act: -0.1700
Data Index: 7000977 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1599. Min Range: -4.1599
Max Act: 3.9723. Min Act: -0.1700
Data Index: 644994 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1599. Min Range: -4.1599
Max Act: 3.9723. Min Act: -0.1700
Data Index: 3943762 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1599. Min Range: -4.1599
Max Act: 3.9723. Min Act: -0.1700
Data Index: 2269411 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0036. Min Act: -0.1700
Data Index: 1013769 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1599. Min Range: -4.1599
Max Act: 4.0036. Min Act: -0.1700
Data Index: 2226321 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1599. Min Range: -4.1599
Max Act: 3.9411. Min Act: -0.1700
Data Index: 6126733 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19