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

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

Neuron 894 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.6001. Min Act: -0.0000

Data Index: 7434 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.9849. Min Act: -0.0000

Data Index: 186622 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.8269. Min Act: -0.0000

Data Index: 704724 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.9267. Min Act: -0.0000

Data Index: 238174 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.8300. Min Act: -0.0000

Data Index: 1105461 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.8241. Min Act: -0.0000

Data Index: 5805 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.7175. Min Act: -0.0000

Data Index: 858933 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.6469. Min Act: -0.0000

Data Index: 583456 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.6287. Min Act: -0.0000

Data Index: 591112 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.6619. Min Act: -0.0000

Data Index: 590938 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.3222. Min Act: -0.0000

Data Index: 162676 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.3573. Min Act: -0.0000

Data Index: 582255 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.3328. Min Act: -0.0000

Data Index: 942242 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.3366. Min Act: -0.0000

Data Index: 336344 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.4436. Min Act: -0.0000

Data Index: 1185062 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.2842. Min Act: -0.0000

Data Index: 196283 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.1755. Min Act: -0.0000

Data Index: 770733 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.1666. Min Act: -0.0000

Data Index: 669870 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.2488. Min Act: -0.0000

Data Index: 550107 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 3.6001. Min Range: -3.6001

Max Act: 2.2319. Min Act: -0.0000

Data Index: 998309 (C4 (Web Text))

Max Activating Token Index: 664