Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 57 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1233593 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0409. Min Act: -0.0001

Data Index: 594434 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0379. Min Act: -0.0001

Data Index: 193550 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0383. Min Act: -0.0001

Data Index: 371767 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0379. Min Act: -0.0001

Data Index: 516652 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1248494 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0330. Min Act: -0.0001

Data Index: 123181 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0363. Min Act: -0.0001

Data Index: 502964 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0297. Min Act: -0.0001

Data Index: 479078 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1198932 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0277. Min Act: -0.0001

Data Index: 796233 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1333831 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0291. Min Act: -0.0001

Data Index: 64392 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1252283 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0250. Min Act: -0.0001

Data Index: 216201 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0243. Min Act: -0.0001

Data Index: 351197 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1197811 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0251. Min Act: -0.0001

Data Index: 163501 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0248. Min Act: -0.0001

Data Index: 251447 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0238. Min Act: -0.0001

Data Index: 71504 (C4 (Web Text))

Max Activating Token Index: 684