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

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

Neuron 1891 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1065. Min Range: -1.1065

Max Act: 1.1065. Min Act: -0.0001

Data Index: 981856 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8883. Min Act: -0.0001

Data Index: 855174 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.9306. Min Act: -0.0001

Data Index: 1402430 (Python Code)

Max Activating Token Index: 572

Text #3

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.9046. Min Act: -0.0001

Data Index: 1095543 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8761. Min Act: -0.0001

Data Index: 694606 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8339. Min Act: -0.0001

Data Index: 714703 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7994. Min Act: -0.0001

Data Index: 805474 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8143. Min Act: -0.0001

Data Index: 616768 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8035. Min Act: -0.0001

Data Index: 879612 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7862. Min Act: -0.0001

Data Index: 1388800 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7336. Min Act: -0.0001

Data Index: 90172 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8043. Min Act: -0.0001

Data Index: 640718 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7232. Min Act: -0.0001

Data Index: 757886 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7777. Min Act: -0.0001

Data Index: 221472 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7773. Min Act: -0.0001

Data Index: 219336 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7269. Min Act: -0.0001

Data Index: 61181 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7358. Min Act: -0.0001

Data Index: 1231448 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7153. Min Act: -0.0001

Data Index: 568610 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7564. Min Act: -0.0001

Data Index: 385099 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7294. Min Act: -0.0001

Data Index: 1323239 (C4 (Web Text))

Max Activating Token Index: 120