Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 112 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1010884 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1193213 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0402. Min Act: -0.0002

Data Index: 928564 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0393. Min Act: -0.0003

Data Index: 307645 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1032621 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1386813 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0369. Min Act: -0.0004

Data Index: 804280 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0367. Min Act: -0.0003

Data Index: 282523 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0345. Min Act: -0.0003

Data Index: 191752 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0336. Min Act: -0.0003

Data Index: 909286 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0343. Min Act: -0.0003

Data Index: 283271 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1050799 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1102980 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1198865 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1276229 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0354. Min Act: -0.0003

Data Index: 425237 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0334. Min Act: -0.0003

Data Index: 701755 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0320. Min Act: -0.0003

Data Index: 519808 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0300. Min Act: -0.0003

Data Index: 832472 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1200440 (C4 (Web Text))

Max Activating Token Index: 359