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

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

Neuron 1114 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1109952 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0412. Min Act: -0.0003

Data Index: 705634 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1072671 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0389. Min Act: -0.0001

Data Index: 1619446 (Python Code)

Max Activating Token Index: 577

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0375. Min Act: 0.0000

Data Index: 1414864 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1544136 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1438397 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1515433 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1567282 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1481011 (Python Code)

Max Activating Token Index: 536

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1400503 (Python Code)

Max Activating Token Index: 359

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1576726 (Python Code)

Max Activating Token Index: 809

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1508318 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1465841 (Python Code)

Max Activating Token Index: 577

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0349. Min Act: -0.0002

Data Index: 58972 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1476543 (Python Code)

Max Activating Token Index: 1018

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1570064 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1579704 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0358. Min Act: -0.0001

Data Index: 336713 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1649610 (Python Code)

Max Activating Token Index: 566