Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4127 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0888. Min Range: -4.0888

Max Act: 4.0490. Min Act: -0.0000

Data Index: 280605 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 4.0888. Min Range: -4.0888

Max Act: 4.0888. Min Act: -0.0000

Data Index: 1303871 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.7230. Min Act: -0.0000

Data Index: 698192 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.6256. Min Act: -0.0000

Data Index: 1202298 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.4357. Min Act: -0.0000

Data Index: 408429 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.4043. Min Act: -0.0000

Data Index: 243933 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.3087. Min Act: -0.0000

Data Index: 364168 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.0062. Min Act: -0.0000

Data Index: 1627407 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.5520. Min Act: -0.0000

Data Index: 916728 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.2333. Min Act: -0.0000

Data Index: 1188997 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.9668. Min Act: -0.0000

Data Index: 398992 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.2318. Min Act: -0.0000

Data Index: 273920 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.0712. Min Act: -0.0000

Data Index: 339510 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.0739. Min Act: -0.0000

Data Index: 932874 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.9289. Min Act: -0.0000

Data Index: 996809 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.0346. Min Act: -0.0000

Data Index: 585160 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.9052. Min Act: -0.0000

Data Index: 714269 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.9990. Min Act: -0.0000

Data Index: 904457 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.9862. Min Act: -0.0000

Data Index: 622282 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.8202. Min Act: -0.0000

Data Index: 569456 (C4 (Web Text))

Max Activating Token Index: 776