Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1963 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7972. Min Act: -0.0002

Data Index: 733333 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.8178. Min Act: -0.0002

Data Index: 623155 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6794. Min Act: -0.0002

Data Index: 1321518 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6826. Min Act: -0.0002

Data Index: 68686 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7386. Min Act: -0.0001

Data Index: 1600706 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7866. Min Act: -0.0001

Data Index: 332236 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6170. Min Act: -0.0002

Data Index: 461643 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6614. Min Act: -0.0002

Data Index: 1132460 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6255. Min Act: -0.0001

Data Index: 1587574 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6457. Min Act: -0.0002

Data Index: 199935 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6840. Min Act: -0.0002

Data Index: 77894 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6424. Min Act: -0.0002

Data Index: 698389 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6538. Min Act: -0.0002

Data Index: 1621635 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5854. Min Act: -0.0001

Data Index: 1437565 (Python Code)

Max Activating Token Index: 314

Text #14

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5842. Min Act: -0.0001

Data Index: 1638269 (Python Code)

Max Activating Token Index: 360

Text #15

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6357. Min Act: -0.0002

Data Index: 1295238 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1579160 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6182. Min Act: -0.0002

Data Index: 1247557 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5566. Min Act: -0.0001

Data Index: 1377705 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5925. Min Act: -0.0001

Data Index: 752283 (C4 (Web Text))

Max Activating Token Index: 402