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

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

Neuron 4165 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.7228. Min Act: -0.0000

Data Index: 604465 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1334278 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6933. Min Act: -0.0000

Data Index: 599744 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6486. Min Act: -0.0000

Data Index: 801345 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1161245 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6549. Min Act: -0.0000

Data Index: 380794 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6542. Min Act: -0.0000

Data Index: 781755 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6250. Min Act: -0.0001

Data Index: 855479 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1335627 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6263. Min Act: -0.0000

Data Index: 12007 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6245. Min Act: -0.0000

Data Index: 822282 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1297361 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1077475 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6332. Min Act: -0.0000

Data Index: 17622 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5948. Min Act: -0.0000

Data Index: 728172 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6233. Min Act: -0.0000

Data Index: 130075 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5836. Min Act: -0.0000

Data Index: 585781 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6258. Min Act: -0.0000

Data Index: 627649 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1296436 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5873. Min Act: -0.0000

Data Index: 302052 (C4 (Web Text))

Max Activating Token Index: 327