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

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

Neuron 2450 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: 0.3300. Min Range: -0.3300

Max Act: 0.3300. Min Act: -0.0000

Data Index: 532316 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2974. Min Act: -0.0000

Data Index: 177657 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2702. Min Act: -0.0000

Data Index: 539651 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1307155 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2466. Min Act: -0.0000

Data Index: 55981 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2352. Min Act: -0.0000

Data Index: 6891 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2241. Min Act: -0.0000

Data Index: 963845 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2150. Min Act: -0.0000

Data Index: 651130 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2181. Min Act: -0.0000

Data Index: 40266 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2490. Min Act: -0.0000

Data Index: 471869 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2305. Min Act: -0.0000

Data Index: 879301 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2237. Min Act: -0.0000

Data Index: 197574 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2302. Min Act: -0.0000

Data Index: 99552 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2140. Min Act: -0.0000

Data Index: 312500 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2090. Min Act: -0.0000

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1334136 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2240. Min Act: -0.0000

Data Index: 331212 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1005341 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1205801 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2177. Min Act: -0.0000

Data Index: 972613 (C4 (Web Text))

Max Activating Token Index: 526