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

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

Neuron 3410 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: 0.3729. Min Range: -0.3729

Max Act: 0.3348. Min Act: -0.0000

Data Index: 93427 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1013889 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1248226 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3380. Min Act: -0.0000

Data Index: 940427 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1242056 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3127. Min Act: -0.0000

Data Index: 338579 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2887. Min Act: -0.0000

Data Index: 264087 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1269736 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2589. Min Act: -0.0000

Data Index: 330176 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1165961 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2645. Min Act: -0.0000

Data Index: 93535 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2832. Min Act: -0.0000

Data Index: 669504 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2659. Min Act: -0.0000

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1341761 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2619. Min Act: -0.0000

Data Index: 180791 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1104424 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1056181 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2893. Min Act: -0.0000

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2347. Min Act: -0.0000

Data Index: 886728 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1262887 (C4 (Web Text))

Max Activating Token Index: 252