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

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

Neuron 1785 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: 0.3231. Min Range: -0.3231

Max Act: 0.3170. Min Act: -0.0001

Data Index: 90273 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3231. Min Act: -0.0001

Data Index: 645517 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2614. Min Act: -0.0001

Data Index: 1093877 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2729. Min Act: -0.0001

Data Index: 742852 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2613. Min Act: -0.0001

Data Index: 188506 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2566. Min Act: -0.0001

Data Index: 783103 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2590. Min Act: -0.0001

Data Index: 214393 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1096830 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2108. Min Act: -0.0001

Data Index: 157412 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2260. Min Act: -0.0001

Data Index: 56132 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2231. Min Act: -0.0001

Data Index: 201725 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2367. Min Act: -0.0001

Data Index: 250155 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2292. Min Act: -0.0001

Data Index: 562647 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2376. Min Act: -0.0001

Data Index: 714112 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2273. Min Act: -0.0001

Data Index: 531875 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2281. Min Act: -0.0001

Data Index: 531640 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2418. Min Act: -0.0001

Data Index: 617966 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1263824 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2020. Min Act: -0.0001

Data Index: 992220 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2327. Min Act: -0.0001

Data Index: 957304 (C4 (Web Text))

Max Activating Token Index: 550