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

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

Neuron 616 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0000

Data Index: 266081 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0276. Min Act: -0.0000

Data Index: 1636763 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0226. Min Act: -0.0000

Data Index: 1636418 (Python Code)

Max Activating Token Index: 425

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0237. Min Act: -0.0000

Data Index: 570161 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1463462 (Python Code)

Max Activating Token Index: 464

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0220. Min Act: -0.0000

Data Index: 93514 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0198. Min Act: -0.0000

Data Index: 680155 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0169. Min Act: -0.0000

Data Index: 1638071 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0185. Min Act: -0.0000

Data Index: 779464 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0213. Min Act: -0.0000

Data Index: 586495 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0195. Min Act: -0.0000

Data Index: 728431 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0181. Min Act: -0.0000

Data Index: 774163 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0186. Min Act: -0.0000

Data Index: 618740 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0169. Min Act: -0.0000

Data Index: 1417166 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0167. Min Act: -0.0000

Data Index: 1429144 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0191. Min Act: -0.0000

Data Index: 1649099 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0172. Min Act: -0.0000

Data Index: 226928 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0176. Min Act: -0.0000

Data Index: 1263807 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0194. Min Act: -0.0000

Data Index: 75229 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0179. Min Act: -0.0000

Data Index: 1588551 (Python Code)

Max Activating Token Index: 752