Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1637 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.2019. Min Act: -0.0001

Data Index: 102959 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1471. Min Act: -0.0001

Data Index: 827114 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1651. Min Act: -0.0001

Data Index: 459954 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1541. Min Act: -0.0001

Data Index: 652732 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1632. Min Act: -0.0001

Data Index: 793231 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1407. Min Act: -0.0001

Data Index: 981530 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1626. Min Act: -0.0000

Data Index: 981303 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1469. Min Act: -0.0000

Data Index: 497961 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1463. Min Act: -0.0001

Data Index: 461030 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1359. Min Act: -0.0001

Data Index: 377340 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1478. Min Act: -0.0000

Data Index: 197125 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1284409 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1310. Min Act: -0.0000

Data Index: 502649 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1448879 (Python Code)

Max Activating Token Index: 570

Text #14

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1345. Min Act: -0.0000

Data Index: 891949 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1283893 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1463891 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1418. Min Act: -0.0000

Data Index: 655353 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1419. Min Act: -0.0001

Data Index: 990261 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.2019. Min Range: -0.2019

Max Act: 0.1455. Min Act: -0.0000

Data Index: 791352 (C4 (Web Text))

Max Activating Token Index: 421