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

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

Neuron 628 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: 0.0433. Min Range: -0.0433

Max Act: 0.0414. Min Act: -0.0003

Data Index: 828154 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1098204 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1184478 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0003

Data Index: 210386 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1407542 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0409. Min Act: -0.0004

Data Index: 829509 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0402. Min Act: -0.0003

Data Index: 55549 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0406. Min Act: -0.0003

Data Index: 384295 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0394. Min Act: -0.0003

Data Index: 296210 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1247167 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0395. Min Act: -0.0003

Data Index: 351142 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0384. Min Act: -0.0003

Data Index: 836673 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1490963 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0402. Min Act: -0.0003

Data Index: 498502 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0394. Min Act: -0.0003

Data Index: 5476 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0395. Min Act: -0.0003

Data Index: 149724 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1535090 (Python Code)

Max Activating Token Index: 502

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1216498 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1366966 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0387. Min Act: -0.0003

Data Index: 168256 (C4 (Web Text))

Max Activating Token Index: 783