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

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

Neuron 4710 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: 0.6235. Min Range: -0.6235

Max Act: 0.6235. Min Act: -0.0000

Data Index: 473285 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1209065 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4743. Min Act: -0.0000

Data Index: 283780 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1202441 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1207794 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4876. Min Act: -0.0000

Data Index: 999429 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4474. Min Act: -0.0000

Data Index: 950201 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4351. Min Act: -0.0000

Data Index: 501711 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4444. Min Act: -0.0000

Data Index: 717892 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1166534 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4036. Min Act: -0.0000

Data Index: 69404 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1259157 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1086925 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1136649 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.3872. Min Act: -0.0000

Data Index: 950508 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4002. Min Act: -0.0000

Data Index: 931670 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4243. Min Act: -0.0000

Data Index: 539238 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.3960. Min Act: -0.0000

Data Index: 136592 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4576. Min Act: -0.0000

Data Index: 585663 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.3694. Min Act: -0.0000

Data Index: 788842 (C4 (Web Text))

Max Activating Token Index: 627