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

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

Neuron 5601 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0485. Min Range: -4.0485

Max Act: 4.0485. Min Act: -0.0000

Data Index: 1232358 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.2712. Min Act: -0.0000

Data Index: 1616205 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.1148. Min Act: -0.0000

Data Index: 657537 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 4.0485. Min Range: -4.0485

Max Act: 2.3244. Min Act: -0.0000

Data Index: 853611 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 4.0485. Min Range: -4.0485

Max Act: 2.3315. Min Act: -0.0000

Data Index: 578484 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 4.0485. Min Range: -4.0485

Max Act: 2.2193. Min Act: -0.0000

Data Index: 1270866 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 4.0485. Min Range: -4.0485

Max Act: 2.3246. Min Act: -0.0000

Data Index: 1591269 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 4.0485. Min Range: -4.0485

Max Act: 2.1594. Min Act: -0.0000

Data Index: 1269708 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 4.0485. Min Range: -4.0485

Max Act: 2.0200. Min Act: -0.0000

Data Index: 1187683 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 4.0485. Min Range: -4.0485

Max Act: 2.0001. Min Act: -0.0000

Data Index: 705112 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.6228. Min Act: -0.0000

Data Index: 426720 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.9281. Min Act: -0.0001

Data Index: 665444 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.9770. Min Act: -0.0000

Data Index: 316054 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.9878. Min Act: -0.0001

Data Index: 2627 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.7808. Min Act: -0.0001

Data Index: 323141 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.9372. Min Act: -0.0000

Data Index: 896036 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 4.0485. Min Range: -4.0485

Max Act: 2.0224. Min Act: -0.0000

Data Index: 681235 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.8789. Min Act: -0.0001

Data Index: 781412 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.9959. Min Act: -0.0000

Data Index: 1498189 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 4.0485. Min Range: -4.0485

Max Act: 1.8736. Min Act: -0.0000

Data Index: 702570 (C4 (Web Text))

Max Activating Token Index: 973