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

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

Neuron 3704 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: 0.5046. Min Range: -0.5046

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1546680 (Python Code)

Max Activating Token Index: 205

Text #1

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1554549 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1441207 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.4453. Min Act: -0.0000

Data Index: 635014 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.4201. Min Act: -0.0001

Data Index: 439252 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1182773 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3911. Min Act: -0.0000

Data Index: 85921 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.4027. Min Act: -0.0001

Data Index: 1419513 (Python Code)

Max Activating Token Index: 341

Text #8

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1444792 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3851. Min Act: -0.0000

Data Index: 575361 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.4254. Min Act: -0.0000

Data Index: 643205 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1496004 (Python Code)

Max Activating Token Index: 207

Text #12

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1442430 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1368966 (Python Code)

Max Activating Token Index: 636

Text #14

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3627. Min Act: -0.0000

Data Index: 481689 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3381. Min Act: -0.0001

Data Index: 238390 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1252069 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3507. Min Act: -0.0000

Data Index: 151053 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1250182 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.5046. Min Range: -0.5046

Max Act: 0.3511. Min Act: -0.0000

Data Index: 482169 (C4 (Web Text))

Max Activating Token Index: 248