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

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

Neuron 4046 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6584. Min Act: 0.0000

Data Index: 70565 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1284379 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1264896 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5646. Min Act: -0.0000

Data Index: 565909 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1336891 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5368. Min Act: -0.0000

Data Index: 763691 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5336. Min Act: -0.0000

Data Index: 364569 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1038048 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1275515 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4626. Min Act: -0.0000

Data Index: 360451 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4545. Min Act: -0.0000

Data Index: 312488 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4475. Min Act: -0.0000

Data Index: 253444 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1052363 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4426. Min Act: -0.0000

Data Index: 126747 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1357889 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4208. Min Act: -0.0000

Data Index: 698637 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4304. Min Act: -0.0000

Data Index: 47198 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4222. Min Act: -0.0000

Data Index: 237551 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1293013 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1094695 (C4 (Web Text))

Max Activating Token Index: 275