Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 810 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4870. Min Act: -0.0001

Data Index: 366511 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4695. Min Act: -0.0001

Data Index: 356879 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.5271. Min Act: -0.0001

Data Index: 436362 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4580. Min Act: -0.0001

Data Index: 724466 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1021948 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4497. Min Act: -0.0001

Data Index: 144535 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4577. Min Act: -0.0001

Data Index: 1329711 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4412. Min Act: -0.0001

Data Index: 474620 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4324. Min Act: -0.0001

Data Index: 947713 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4415. Min Act: -0.0001

Data Index: 23272 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4251. Min Act: -0.0001

Data Index: 334197 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4454. Min Act: -0.0001

Data Index: 886836 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4155. Min Act: -0.0001

Data Index: 491321 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4277. Min Act: -0.0001

Data Index: 139190 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4263. Min Act: -0.0001

Data Index: 634041 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4262. Min Act: -0.0001

Data Index: 762399 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4264. Min Act: -0.0001

Data Index: 1303034 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4102. Min Act: -0.0001

Data Index: 618440 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4028. Min Act: -0.0001

Data Index: 44496 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.5271. Min Range: -0.5271

Max Act: 0.4281. Min Act: -0.0001

Data Index: 259260 (C4 (Web Text))

Max Activating Token Index: 850