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

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

Neuron 5349 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: 0.7670. Min Range: -0.7670

Max Act: 0.7670. Min Act: -0.0000

Data Index: 885050 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1192484 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7443. Min Act: -0.0000

Data Index: 26467 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7062. Min Act: -0.0000

Data Index: 685267 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1233368 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1320400 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6292. Min Act: -0.0000

Data Index: 364608 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5994. Min Act: -0.0000

Data Index: 671808 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6123. Min Act: -0.0000

Data Index: 743946 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5852. Min Act: -0.0000

Data Index: 817611 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1539 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5921. Min Act: -0.0000

Data Index: 995253 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5538. Min Act: -0.0000

Data Index: 449348 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5668. Min Act: -0.0000

Data Index: 457835 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5619. Min Act: -0.0000

Data Index: 891594 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1229945 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5268. Min Act: -0.0000

Data Index: 481280 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5394. Min Act: -0.0000

Data Index: 268374 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1018599 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5186. Min Act: -0.0000

Data Index: 360205 (C4 (Web Text))

Max Activating Token Index: 354