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

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

Neuron 5820 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1196405 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1031305 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3466. Min Act: -0.0000

Data Index: 345833 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3832. Min Act: -0.0001

Data Index: 388195 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3366. Min Act: -0.0000

Data Index: 379116 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3471. Min Act: -0.0000

Data Index: 163555 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3683. Min Act: -0.0000

Data Index: 191627 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3842. Min Act: -0.0001

Data Index: 375366 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3433. Min Act: -0.0000

Data Index: 75661 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3847. Min Act: -0.0000

Data Index: 289106 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1219013 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3693. Min Act: -0.0000

Data Index: 796116 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3666. Min Act: -0.0000

Data Index: 837657 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1226409 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3371. Min Act: -0.0001

Data Index: 1137300 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3275. Min Act: -0.0000

Data Index: 381947 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1107514 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1304361 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3695. Min Act: -0.0000

Data Index: 711091 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.4424. Min Range: -0.4424

Max Act: 0.3476. Min Act: -0.0000

Data Index: 22238 (C4 (Web Text))

Max Activating Token Index: 32