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

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

Neuron 1792 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: 0.2899. Min Range: -0.2899

Max Act: 0.2899. Min Act: -0.0001

Data Index: 360148 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2779. Min Act: -0.0001

Data Index: 661902 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2689. Min Act: -0.0001

Data Index: 101334 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2049. Min Act: -0.0001

Data Index: 542960 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1159546 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2322. Min Act: -0.0001

Data Index: 410909 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1071124 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2370. Min Act: -0.0001

Data Index: 468979 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2270. Min Act: -0.0001

Data Index: 635907 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2122. Min Act: -0.0001

Data Index: 1293592 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2245. Min Act: -0.0001

Data Index: 1120947 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2240. Min Act: -0.0001

Data Index: 456634 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2211. Min Act: -0.0001

Data Index: 1137522 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2275. Min Act: -0.0001

Data Index: 397768 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2254. Min Act: -0.0001

Data Index: 416410 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2230. Min Act: -0.0001

Data Index: 825434 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2234. Min Act: -0.0001

Data Index: 912818 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2038. Min Act: -0.0001

Data Index: 330971 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1212014 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1912. Min Act: -0.0001

Data Index: 585882 (C4 (Web Text))

Max Activating Token Index: 382