Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3268 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.4098. Min Act: -0.0000

Data Index: 1302582 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.9563. Min Act: -0.0000

Data Index: 1640927 (Python Code)

Max Activating Token Index: 696

Text #2

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.7441. Min Act: -0.0000

Data Index: 1418480 (Python Code)

Max Activating Token Index: 502

Text #3

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.5770. Min Act: -0.0000

Data Index: 1443289 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.7930. Min Act: -0.0000

Data Index: 1547792 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.6435. Min Act: -0.0000

Data Index: 1484206 (Python Code)

Max Activating Token Index: 402

Text #6

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.7581. Min Act: -0.0000

Data Index: 1515662 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.6438. Min Act: -0.0000

Data Index: 1195511 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.5396. Min Act: -0.0000

Data Index: 699753 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.3721. Min Act: -0.0000

Data Index: 617917 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.3691. Min Act: -0.0000

Data Index: 686128 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.2683. Min Act: -0.0000

Data Index: 1249394 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.4718. Min Act: -0.0000

Data Index: 1213861 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.4363. Min Act: -0.0000

Data Index: 1020268 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.0906. Min Act: -0.0000

Data Index: 552027 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.2773. Min Act: -0.0000

Data Index: 1443686 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.5108. Min Act: -0.0000

Data Index: 737485 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1427024 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.1299. Min Act: -0.0000

Data Index: 551656 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 3.4098. Min Range: -3.4098

Max Act: 2.2336. Min Act: -0.0000

Data Index: 264494 (C4 (Web Text))

Max Activating Token Index: 492