Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1512 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.5174. Min Act: -0.0004

Data Index: 1171341 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4855. Min Act: -0.0004

Data Index: 207905 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4680. Min Act: -0.0004

Data Index: 1038507 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4747. Min Act: -0.0004

Data Index: 517906 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4725. Min Act: -0.0004

Data Index: 1251227 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4722. Min Act: -0.0004

Data Index: 892879 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4705. Min Act: -0.0004

Data Index: 760190 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4613. Min Act: -0.0005

Data Index: 394676 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4595. Min Act: -0.0004

Data Index: 49169 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4582. Min Act: -0.0003

Data Index: 817653 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4541. Min Act: -0.0004

Data Index: 245262 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4499. Min Act: -0.0004

Data Index: 928028 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4439. Min Act: -0.0003

Data Index: 1097628 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4429. Min Act: -0.0004

Data Index: 764955 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4266. Min Act: -0.0004

Data Index: 45989 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4264. Min Act: -0.0004

Data Index: 646544 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4554. Min Act: -0.0004

Data Index: 72132 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4385. Min Act: -0.0004

Data Index: 618490 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4387. Min Act: -0.0004

Data Index: 467427 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.5174. Min Range: -0.5174

Max Act: 0.4206. Min Act: -0.0004

Data Index: 54613 (C4 (Web Text))

Max Activating Token Index: 531