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

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

Neuron 894 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8178. Min Range: -1.8178

Max Act: 1.8178. Min Act: -0.0000

Data Index: 689362 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1089671 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.9280. Min Act: -0.0000

Data Index: 469308 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1137833 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.7653. Min Act: -0.0000

Data Index: 828362 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.7851. Min Act: -0.0000

Data Index: 427217 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.7324. Min Act: -0.0000

Data Index: 922936 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1196248 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5880. Min Act: -0.0000

Data Index: 14178 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5751. Min Act: -0.0000

Data Index: 420548 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.6080. Min Act: -0.0000

Data Index: 331817 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5775. Min Act: -0.0000

Data Index: 189848 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1161642 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1132829 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5372. Min Act: -0.0000

Data Index: 623449 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5308. Min Act: -0.0000

Data Index: 72242 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5251. Min Act: 0.0000

Data Index: 111310 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5397. Min Act: -0.0000

Data Index: 943342 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5369. Min Act: -0.0000

Data Index: 448486 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.8178. Min Range: -1.8178

Max Act: 0.5042. Min Act: -0.0000

Data Index: 980890 (C4 (Web Text))

Max Activating Token Index: 895