Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4033 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.7388. Min Act: -0.0000

Data Index: 620385 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.9139. Min Act: -0.0000

Data Index: 261941 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.6320. Min Act: 0.0000

Data Index: 753173 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.5242. Min Act: -0.0000

Data Index: 657118 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.5378. Min Act: -0.0000

Data Index: 1124437 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.4704. Min Act: -0.0000

Data Index: 1285782 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.4514. Min Act: -0.0000

Data Index: 906743 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.3928. Min Act: 0.0000

Data Index: 1004964 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2632. Min Act: -0.0000

Data Index: 831107 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2168. Min Act: -0.0000

Data Index: 550074 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.1982. Min Act: -0.0000

Data Index: 264278 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2809. Min Act: -0.0000

Data Index: 937889 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2731. Min Act: 0.0000

Data Index: 1079837 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2693. Min Act: -0.0000

Data Index: 537905 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2672. Min Act: -0.0000

Data Index: 304354 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2427. Min Act: -0.0000

Data Index: 1246106 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2252. Min Act: -0.0000

Data Index: 470390 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1107173 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 2.9139. Min Range: -2.9139

Max Act: 1.8627. Min Act: -0.0000

Data Index: 725575 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 2.9139. Min Range: -2.9139

Max Act: 2.0881. Min Act: -0.0000

Data Index: 806119 (C4 (Web Text))

Max Activating Token Index: 70