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

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

Neuron 3323 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.3403. Min Act: -0.0002

Data Index: 189581 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.3130. Min Act: -0.0002

Data Index: 1032592 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2988. Min Act: -0.0002

Data Index: 169876 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2843. Min Act: -0.0002

Data Index: 824409 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2205. Min Act: -0.0002

Data Index: 1012035 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2565. Min Act: -0.0002

Data Index: 984996 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2708. Min Act: -0.0002

Data Index: 183023 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2716. Min Act: -0.0002

Data Index: 780433 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2831. Min Act: -0.0002

Data Index: 1049032 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2396. Min Act: -0.0002

Data Index: 588185 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2271. Min Act: -0.0002

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2400. Min Act: -0.0002

Data Index: 1198152 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2412. Min Act: -0.0002

Data Index: 372488 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2237. Min Act: -0.0002

Data Index: 601 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2323. Min Act: -0.0002

Data Index: 1190497 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2204. Min Act: -0.0002

Data Index: 165472 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2275. Min Act: -0.0002

Data Index: 974776 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2263. Min Act: -0.0002

Data Index: 250166 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2371. Min Act: -0.0002

Data Index: 1143720 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2123. Min Act: -0.0002

Data Index: 225562 (C4 (Web Text))

Max Activating Token Index: 494