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

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

Neuron 3293 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.5141. Min Act: -0.0002

Data Index: 617380 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4823. Min Act: -0.0001

Data Index: 435539 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4837. Min Act: -0.0001

Data Index: 626385 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4625. Min Act: -0.0001

Data Index: 877525 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4532. Min Act: -0.0001

Data Index: 242461 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4620. Min Act: -0.0001

Data Index: 817657 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4062. Min Act: -0.0002

Data Index: 350276 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.5003. Min Act: -0.0002

Data Index: 12880 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4454. Min Act: -0.0001

Data Index: 61519 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4319. Min Act: -0.0001

Data Index: 824314 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4356. Min Act: -0.0001

Data Index: 1043958 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4299. Min Act: -0.0001

Data Index: 251593 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4110. Min Act: -0.0001

Data Index: 10441 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4374. Min Act: -0.0001

Data Index: 914289 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4105. Min Act: -0.0001

Data Index: 192661 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4159. Min Act: -0.0001

Data Index: 960747 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4165. Min Act: -0.0001

Data Index: 29085 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4040. Min Act: -0.0001

Data Index: 711984 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.3724. Min Act: -0.0002

Data Index: 695980 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.3976. Min Act: -0.0001

Data Index: 802215 (C4 (Web Text))

Max Activating Token Index: 99