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

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

Neuron 1049 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2901. Min Act: -0.0001

Data Index: 739563 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1093777 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2290. Min Act: -0.0001

Data Index: 789534 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2445. Min Act: -0.0000

Data Index: 552833 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2416. Min Act: -0.0001

Data Index: 658797 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2520. Min Act: -0.0001

Data Index: 5689 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1194631 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2394. Min Act: -0.0001

Data Index: 634514 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2303. Min Act: -0.0001

Data Index: 176478 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2241. Min Act: -0.0001

Data Index: 625944 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2219. Min Act: -0.0001

Data Index: 437373 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2238. Min Act: -0.0001

Data Index: 376313 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2366. Min Act: -0.0001

Data Index: 318031 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2356. Min Act: -0.0001

Data Index: 282724 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2261. Min Act: -0.0000

Data Index: 480078 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2348. Min Act: -0.0000

Data Index: 412878 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2249. Min Act: -0.0000

Data Index: 568134 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2252. Min Act: -0.0000

Data Index: 839204 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2242. Min Act: -0.0001

Data Index: 634942 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1350997 (C4 (Web Text))

Max Activating Token Index: 368