Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2544 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.6663. Min Act: -0.0000

Data Index: 258306 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1040183 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.2883. Min Act: -0.0000

Data Index: 416783 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.6663. Min Range: -1.6663

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1340083 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.9426. Min Act: -0.0000

Data Index: 792481 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8572. Min Act: -0.0000

Data Index: 925587 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.9347. Min Act: -0.0000

Data Index: 488495 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.9169. Min Act: -0.0000

Data Index: 434548 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.9177. Min Act: -0.0000

Data Index: 749908 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8560. Min Act: -0.0000

Data Index: 551254 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.9289. Min Act: -0.0000

Data Index: 803380 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1292193 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8003. Min Act: -0.0000

Data Index: 107369 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8385. Min Act: -0.0000

Data Index: 346471 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8074. Min Act: -0.0000

Data Index: 526957 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8524. Min Act: -0.0000

Data Index: 68691 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8252. Min Act: -0.0000

Data Index: 413062 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1140529 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8804. Min Act: -0.0000

Data Index: 53364 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.6663. Min Range: -1.6663

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1139763 (C4 (Web Text))

Max Activating Token Index: 826