Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4539 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.5263. Min Act: -0.0001

Data Index: 164332 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.4168. Min Act: -0.0001

Data Index: 1045103 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.4099. Min Act: -0.0001

Data Index: 1287261 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2414. Min Act: -0.0001

Data Index: 841010 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.3770. Min Act: -0.0001

Data Index: 427529 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.3128. Min Act: -0.0001

Data Index: 609859 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2134. Min Act: -0.0001

Data Index: 1203992 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.3119. Min Act: -0.0001

Data Index: 1250372 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.3234. Min Act: -0.0001

Data Index: 522561 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2172. Min Act: -0.0001

Data Index: 705759 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.3530. Min Act: -0.0001

Data Index: 172013 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2000. Min Act: -0.0001

Data Index: 153302 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2477. Min Act: -0.0001

Data Index: 1120851 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1790. Min Act: -0.0001

Data Index: 456443 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1790. Min Act: -0.0001

Data Index: 212540 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0802. Min Act: -0.0001

Data Index: 964893 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1027. Min Act: -0.0001

Data Index: 18845 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0880. Min Act: -0.0001

Data Index: 823127 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1379. Min Act: -0.0001

Data Index: 1119880 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1898. Min Act: -0.0002

Data Index: 816678 (C4 (Web Text))

Max Activating Token Index: 6