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

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

Neuron 4214 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1104923 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.2319. Min Act: 0.0000

Data Index: 736546 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.1496. Min Act: -0.0000

Data Index: 908116 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.0792. Min Act: -0.0000

Data Index: 401475 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.0165. Min Act: -0.0000

Data Index: 699569 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.9632. Min Act: -0.0000

Data Index: 946047 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.0016. Min Act: -0.0000

Data Index: 256901 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1270257 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.9266. Min Act: -0.0000

Data Index: 980859 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1278252 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7676. Min Act: -0.0000

Data Index: 7680 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1248650 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8911. Min Act: -0.0000

Data Index: 388896 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8669. Min Act: -0.0000

Data Index: 28450 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8249. Min Act: -0.0000

Data Index: 369313 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8592. Min Act: -0.0000

Data Index: 709561 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8382. Min Act: -0.0000

Data Index: 87969 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1323702 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7834. Min Act: 0.0000

Data Index: 761079 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1126382 (C4 (Web Text))

Max Activating Token Index: 235