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

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

Neuron 2256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3543. Min Act: 0.0000

Data Index: 1394635 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3161. Min Act: -0.0001

Data Index: 1590699 (Python Code)

Max Activating Token Index: 319

Text #2

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3180. Min Act: -0.0001

Data Index: 1586509 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3208. Min Act: 0.0001

Data Index: 895025 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3089. Min Act: -0.0000

Data Index: 168415 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2989. Min Act: -0.0000

Data Index: 557345 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2816. Min Act: 0.0001

Data Index: 1194001 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2690. Min Act: -0.0001

Data Index: 1160198 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2772. Min Act: 0.0001

Data Index: 1048374 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2714. Min Act: -0.0000

Data Index: 388529 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2642. Min Act: -0.0001

Data Index: 145612 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2696. Min Act: -0.0001

Data Index: 423600 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1408662 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2343. Min Act: -0.0001

Data Index: 968417 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1361524 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2306. Min Act: -0.0000

Data Index: 92231 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2251. Min Act: -0.0001

Data Index: 577209 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2244. Min Act: -0.0001

Data Index: 800972 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2129. Min Act: -0.0001

Data Index: 848794 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2177. Min Act: 0.0001

Data Index: 1164219 (C4 (Web Text))

Max Activating Token Index: 120