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

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

Neuron 4508 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0001

Data Index: 364596 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0388. Min Act: -0.0001

Data Index: 826878 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0285. Min Act: -0.0001

Data Index: 383804 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1026517 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0300. Min Act: -0.0001

Data Index: 711180 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1073294 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1245309 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0257. Min Act: -0.0001

Data Index: 817034 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1318827 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0258. Min Act: -0.0001

Data Index: 369765 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0245. Min Act: -0.0001

Data Index: 828970 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0255. Min Act: -0.0001

Data Index: 340937 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1276897 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0246. Min Act: -0.0001

Data Index: 175898 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1356444 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0233. Min Act: -0.0001

Data Index: 880517 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0243. Min Act: -0.0001

Data Index: 777643 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0234. Min Act: -0.0001

Data Index: 683862 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0224. Min Act: -0.0001

Data Index: 303341 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0227. Min Act: -0.0001

Data Index: 749473 (C4 (Web Text))

Max Activating Token Index: 424