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

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

Neuron 2211 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: 0.4012. Min Range: -0.4012

Max Act: 0.4012. Min Act: -0.0001

Data Index: 1130819 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.3248. Min Act: -0.0000

Data Index: 407526 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2788. Min Act: -0.0001

Data Index: 61352 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2675. Min Act: -0.0000

Data Index: 156738 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2587. Min Act: -0.0001

Data Index: 952831 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2533. Min Act: -0.0000

Data Index: 121463 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2455. Min Act: -0.0000

Data Index: 910841 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2408. Min Act: -0.0000

Data Index: 563332 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2363. Min Act: -0.0001

Data Index: 422127 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2189. Min Act: -0.0001

Data Index: 221089 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2254. Min Act: -0.0001

Data Index: 390295 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2219. Min Act: -0.0001

Data Index: 780880 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2276. Min Act: -0.0000

Data Index: 816369 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2196. Min Act: -0.0000

Data Index: 894334 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2175. Min Act: -0.0001

Data Index: 748985 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2158. Min Act: -0.0001

Data Index: 1072968 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2240. Min Act: -0.0000

Data Index: 676507 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2213. Min Act: -0.0001

Data Index: 1306127 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2185. Min Act: -0.0000

Data Index: 586360 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.4012. Min Range: -0.4012

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1215843 (C4 (Web Text))

Max Activating Token Index: 434