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

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

Neuron 3985 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: 0.9385. Min Range: -0.9385

Max Act: 0.9385. Min Act: -0.0001

Data Index: 747697 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.8752. Min Act: -0.0001

Data Index: 1106211 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.8570. Min Act: -0.0000

Data Index: 954411 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7831. Min Act: -0.0000

Data Index: 350548 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7739. Min Act: -0.0001

Data Index: 1063432 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1174662 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7925. Min Act: -0.0000

Data Index: 619788 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7708. Min Act: -0.0001

Data Index: 1015615 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7894. Min Act: -0.0000

Data Index: 811214 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.8279. Min Act: -0.0000

Data Index: 627092 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7757. Min Act: -0.0001

Data Index: 302981 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7795. Min Act: -0.0001

Data Index: 1329339 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7488. Min Act: -0.0000

Data Index: 963393 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1087145 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6973. Min Act: -0.0000

Data Index: 600775 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6770. Min Act: -0.0001

Data Index: 197721 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6888. Min Act: -0.0001

Data Index: 730949 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7168. Min Act: -0.0000

Data Index: 565505 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7293. Min Act: -0.0001

Data Index: 803193 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6579. Min Act: -0.0000

Data Index: 657043 (C4 (Web Text))

Max Activating Token Index: 994