Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2027 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0347. Min Act: -0.0006

Data Index: 221114 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0322. Min Act: -0.0006

Data Index: 683956 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0337. Min Act: -0.0006

Data Index: 834041 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0345. Min Act: -0.0006

Data Index: 669821 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0314. Min Act: -0.0006

Data Index: 351740 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0326. Min Act: -0.0006

Data Index: 815792 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0330. Min Act: -0.0006

Data Index: 1075296 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0323. Min Act: -0.0006

Data Index: 514765 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0322. Min Act: -0.0006

Data Index: 2646 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0310. Min Act: -0.0006

Data Index: 698167 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0308. Min Act: -0.0006

Data Index: 39866 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0301. Min Act: -0.0006

Data Index: 961778 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0306. Min Act: -0.0006

Data Index: 346512 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1247393 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0318. Min Act: -0.0006

Data Index: 454946 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0308. Min Act: -0.0006

Data Index: 603023 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0307. Min Act: -0.0006

Data Index: 55402 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0299. Min Act: -0.0006

Data Index: 503503 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1145461 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0298. Min Act: -0.0006

Data Index: 47494 (C4 (Web Text))

Max Activating Token Index: 891