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

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

Neuron 2534 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: 0.3235. Min Range: -0.3235

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1037230 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2810. Min Act: -0.0001

Data Index: 995833 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.3006. Min Act: -0.0000

Data Index: 624881 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.3235. Min Act: -0.0000

Data Index: 417232 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1166249 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2552. Min Act: -0.0000

Data Index: 625776 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2713. Min Act: -0.0000

Data Index: 116837 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1068468 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2385. Min Act: -0.0000

Data Index: 151887 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2448. Min Act: -0.0000

Data Index: 386461 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1299281 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1186448 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2211. Min Act: -0.0000

Data Index: 391655 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2234. Min Act: -0.0000

Data Index: 660551 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1007848 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1239530 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2068. Min Act: -0.0000

Data Index: 846280 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2294. Min Act: -0.0000

Data Index: 791594 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1448381 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 0.3235. Min Range: -0.3235

Max Act: 0.2197. Min Act: -0.0000

Data Index: 536874 (C4 (Web Text))

Max Activating Token Index: 946