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

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

Neuron 2909 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.2415. Min Act: -0.0003

Data Index: 408154 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.1384. Min Act: -0.0003

Data Index: 237051 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.0306. Min Act: -0.0002

Data Index: 629519 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.0210. Min Act: -0.0003

Data Index: 438983 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9936. Min Act: -0.0002

Data Index: 912826 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9897. Min Act: -0.0003

Data Index: 620070 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9463. Min Act: -0.0003

Data Index: 965231 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9738. Min Act: -0.0003

Data Index: 323884 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9278. Min Act: -0.0002

Data Index: 382916 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9570. Min Act: -0.0003

Data Index: 11756 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9494. Min Act: -0.0002

Data Index: 561947 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9718. Min Act: -0.0003

Data Index: 157971 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9236. Min Act: -0.0003

Data Index: 1145824 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9028. Min Act: -0.0003

Data Index: 799591 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8749. Min Act: -0.0003

Data Index: 19366 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8954. Min Act: -0.0003

Data Index: 141260 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8963. Min Act: -0.0002

Data Index: 57146 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8918. Min Act: -0.0002

Data Index: 150654 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8919. Min Act: -0.0003

Data Index: 1223467 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8852. Min Act: -0.0003

Data Index: 542860 (C4 (Web Text))

Max Activating Token Index: 334