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

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

Neuron 1285 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1280. Min Range: -2.1280

Max Act: 2.1280. Min Act: -0.0000

Data Index: 759999 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 2.1280. Min Range: -2.1280

Max Act: 2.0177. Min Act: -0.0000

Data Index: 346257 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.8353. Min Act: -0.0000

Data Index: 590994 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.7409. Min Act: -0.0000

Data Index: 1154188 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.9063. Min Act: -0.0000

Data Index: 423837 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.7906. Min Act: -0.0000

Data Index: 518369 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.6209. Min Act: -0.0000

Data Index: 1284874 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.5632. Min Act: -0.0000

Data Index: 319459 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.6586. Min Act: -0.0000

Data Index: 57208 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.6361. Min Act: -0.0000

Data Index: 341912 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.6160. Min Act: -0.0000

Data Index: 927774 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.6163. Min Act: -0.0000

Data Index: 1000087 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.4455. Min Act: -0.0000

Data Index: 3150 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.4503. Min Act: -0.0000

Data Index: 948709 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.5275. Min Act: -0.0000

Data Index: 793006 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.5373. Min Act: -0.0000

Data Index: 218340 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.3874. Min Act: -0.0000

Data Index: 780272 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.3723. Min Act: -0.0000

Data Index: 115212 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.3670. Min Act: -0.0000

Data Index: 1069725 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 2.1280. Min Range: -2.1280

Max Act: 1.5183. Min Act: -0.0000

Data Index: 567373 (C4 (Web Text))

Max Activating Token Index: 796