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

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

Neuron 1542 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.2221. Min Act: -0.0000

Data Index: 71850 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9805. Min Act: -0.0001

Data Index: 1411704 (Python Code)

Max Activating Token Index: 265

Text #2

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9229. Min Act: -0.0000

Data Index: 295531 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9418. Min Act: -0.0000

Data Index: 533789 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8954. Min Act: -0.0000

Data Index: 449232 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8115. Min Act: -0.0001

Data Index: 794506 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1036063 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1329712 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7246. Min Act: -0.0000

Data Index: 928466 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7623. Min Act: -0.0001

Data Index: 1410917 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.6541. Min Act: -0.0000

Data Index: 324031 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7202. Min Act: -0.0000

Data Index: 891031 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1285307 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7364. Min Act: -0.0000

Data Index: 856310 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7241. Min Act: -0.0001

Data Index: 1642641 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7246. Min Act: -0.0000

Data Index: 276937 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.6935. Min Act: -0.0000

Data Index: 960202 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7164. Min Act: -0.0000

Data Index: 975224 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.6970. Min Act: -0.0000

Data Index: 584888 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7366. Min Act: -0.0000

Data Index: 559224 (C4 (Web Text))

Max Activating Token Index: 687