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

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

Neuron 1468 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: 3.9610. Min Range: -3.9610

Max Act: 3.9610. Min Act: -0.0000

Data Index: 757148 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.8112. Min Act: -0.0000

Data Index: 1599725 (Python Code)

Max Activating Token Index: 473

Text #2

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6803. Min Act: -0.0000

Data Index: 1381565 (Python Code)

Max Activating Token Index: 473

Text #3

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.8770. Min Act: -0.0000

Data Index: 1520757 (Python Code)

Max Activating Token Index: 485

Text #4

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6399. Min Act: -0.0000

Data Index: 767220 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.5060. Min Act: -0.0000

Data Index: 102760 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7157. Min Act: -0.0000

Data Index: 573731 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.2290. Min Act: -0.0000

Data Index: 434239 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.5944. Min Act: -0.0000

Data Index: 115550 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.4917. Min Act: -0.0000

Data Index: 742615 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.4159. Min Act: -0.0000

Data Index: 1103919 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.1191. Min Act: -0.0000

Data Index: 480525 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.3958. Min Act: -0.0000

Data Index: 397287 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.9679. Min Act: -0.0000

Data Index: 820643 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.1906. Min Act: -0.0000

Data Index: 1646706 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.3251. Min Act: -0.0000

Data Index: 1578118 (Python Code)

Max Activating Token Index: 1001

Text #16

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.0293. Min Act: -0.0000

Data Index: 1495084 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 3.9610. Min Range: -3.9610

Max Act: 2.8127. Min Act: -0.0000

Data Index: 1458604 (Python Code)

Max Activating Token Index: 248

Text #18

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.1467. Min Act: -0.0000

Data Index: 1245885 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.5244. Min Act: -0.0000

Data Index: 325594 (C4 (Web Text))

Max Activating Token Index: 701