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

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

Neuron 3436 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2453. Min Act: -0.0001

Data Index: 249423 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2666. Min Act: -0.0001

Data Index: 928932 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2606. Min Act: -0.0001

Data Index: 1076003 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2478. Min Act: -0.0001

Data Index: 120414 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1041356 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1065104 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2374. Min Act: -0.0001

Data Index: 798517 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2221. Min Act: -0.0001

Data Index: 126293 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2312. Min Act: -0.0001

Data Index: 527664 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2238. Min Act: -0.0001

Data Index: 207364 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2313. Min Act: -0.0001

Data Index: 397004 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2219. Min Act: -0.0001

Data Index: 79895 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2138. Min Act: -0.0001

Data Index: 1040595 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2211. Min Act: -0.0001

Data Index: 859273 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1953. Min Act: -0.0001

Data Index: 40169 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1979. Min Act: -0.0001

Data Index: 916964 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2266. Min Act: -0.0001

Data Index: 582996 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2254. Min Act: -0.0001

Data Index: 321885 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1899. Min Act: -0.0001

Data Index: 770334 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2040. Min Act: -0.0001

Data Index: 388439 (C4 (Web Text))

Max Activating Token Index: 486