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

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

Neuron 3276 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.8742. Min Act: -0.0000

Data Index: 1295477 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.7596. Min Act: -0.0000

Data Index: 632377 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.6266. Min Act: -0.0000

Data Index: 742045 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.2884. Min Act: -0.0000

Data Index: 924178 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.2690. Min Act: -0.0000

Data Index: 587307 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1254086 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.2146. Min Act: -0.0000

Data Index: 322812 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.2352. Min Act: -0.0000

Data Index: 844608 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1187766 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1058430 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.0842. Min Act: -0.0000

Data Index: 571477 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1169830 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.0469. Min Act: -0.0000

Data Index: 121460 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.1263. Min Act: -0.0000

Data Index: 546422 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1022361 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1282199 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.8742. Min Range: -1.8742

Max Act: 1.0199. Min Act: -0.0000

Data Index: 444930 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 1.8742. Min Range: -1.8742

Max Act: 0.9586. Min Act: -0.0000

Data Index: 967517 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.8742. Min Range: -1.8742

Max Act: 0.9904. Min Act: -0.0000

Data Index: 917026 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 1.8742. Min Range: -1.8742

Max Act: 0.9909. Min Act: -0.0000

Data Index: 130236 (C4 (Web Text))

Max Activating Token Index: 418