Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2646 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1076030 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7892. Min Act: -0.0000

Data Index: 887217 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1082692 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.6835. Min Act: -0.0000

Data Index: 420595 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1188075 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.6003. Min Act: -0.0000

Data Index: 35365 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.5588. Min Act: -0.0000

Data Index: 652531 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1017455 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1315408 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.5168. Min Act: -0.0000

Data Index: 229850 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4734. Min Act: -0.0000

Data Index: 610358 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4617. Min Act: -0.0000

Data Index: 799510 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4855. Min Act: -0.0000

Data Index: 885914 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4334. Min Act: -0.0000

Data Index: 538029 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4331. Min Act: -0.0000

Data Index: 604380 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1079302 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4533. Min Act: -0.0000

Data Index: 908878 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1160198 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1088088 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1329300 (C4 (Web Text))

Max Activating Token Index: 505