Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.7442. Min Act: -0.1700
Data Index: 3399173 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.7442. Min Act: -0.1700
Data Index: 8141009 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.5565. Min Act: -0.1700
Data Index: 3584493 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.5252. Min Act: -0.1700
Data Index: 1843141 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.5252. Min Act: -0.1700
Data Index: 2040183 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4938. Min Act: -0.1700
Data Index: 7661462 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4938. Min Act: -0.1700
Data Index: 8781071 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4938. Min Act: -0.1700
Data Index: 1479845 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4938. Min Act: -0.1700
Data Index: 545338 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4938. Min Act: -0.1700
Data Index: 7039138 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4625. Min Act: -0.1700
Data Index: 1955611 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4312. Min Act: -0.1700
Data Index: 646815 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4625. Min Act: -0.1700
Data Index: 2595929 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4625. Min Act: -0.1700
Data Index: 1745514 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4312. Min Act: -0.1700
Data Index: 3626180 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4312. Min Act: -0.1700
Data Index: 5505597 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4312. Min Act: -0.1700
Data Index: 7514863 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4312. Min Act: -0.1700
Data Index: 3461773 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4155. Min Act: -0.1700
Data Index: 3945513 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7442. Min Range: -3.7442
Max Act: 3.4312. Min Act: -0.1700
Data Index: 5102718 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19