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

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

Neuron 1270 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.7325. Min Act: -0.0000

Data Index: 243737 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.7563. Min Act: -0.0000

Data Index: 285716 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4738. Min Act: -0.0000

Data Index: 551007 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3923. Min Act: -0.0000

Data Index: 318834 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4154. Min Act: -0.0000

Data Index: 434319 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.4145. Min Act: -0.0000

Data Index: 509343 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1153816 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3910. Min Act: -0.0000

Data Index: 909162 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3557. Min Act: -0.0000

Data Index: 28120 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3764. Min Act: -0.0000

Data Index: 872291 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3594. Min Act: -0.0000

Data Index: 696367 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3690. Min Act: -0.0000

Data Index: 953441 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3233. Min Act: -0.0000

Data Index: 461964 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1247288 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3532. Min Act: -0.0000

Data Index: 473946 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3542. Min Act: -0.0000

Data Index: 575936 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3421. Min Act: -0.0000

Data Index: 66685 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3499. Min Act: -0.0000

Data Index: 298999 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3638. Min Act: -0.0000

Data Index: 383109 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.3477. Min Act: -0.0000

Data Index: 844950 (C4 (Web Text))

Max Activating Token Index: 395