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

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

Neuron 4073 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1037615 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8985. Min Act: -0.0000

Data Index: 479645 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1148191 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8914. Min Act: -0.0000

Data Index: 929438 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9872. Min Act: -0.0000

Data Index: 585441 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8477. Min Act: -0.0000

Data Index: 909746 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8358. Min Act: -0.0000

Data Index: 836008 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8416. Min Act: -0.0000

Data Index: 115803 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8224. Min Act: -0.0000

Data Index: 650010 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1126115 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1157671 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8138. Min Act: -0.0000

Data Index: 213042 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8002. Min Act: -0.0000

Data Index: 349986 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8446. Min Act: -0.0000

Data Index: 584340 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7885. Min Act: -0.0000

Data Index: 774712 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7135. Min Act: -0.0000

Data Index: 165590 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8176. Min Act: -0.0000

Data Index: 512185 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8061. Min Act: -0.0000

Data Index: 583357 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7336. Min Act: -0.0000

Data Index: 745093 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1048367 (C4 (Web Text))

Max Activating Token Index: 851