Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 540 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4645. Min Act: -0.0000

Data Index: 874130 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4716. Min Act: -0.0000

Data Index: 835836 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4317. Min Act: -0.0000

Data Index: 891665 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3975. Min Act: -0.0000

Data Index: 142078 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1606422 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3532. Min Act: -0.0000

Data Index: 339544 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3475. Min Act: -0.0000

Data Index: 150016 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3691. Min Act: 0.0000

Data Index: 891494 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3459. Min Act: -0.0000

Data Index: 330102 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3581. Min Act: -0.0000

Data Index: 830478 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1135655 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1133075 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1107191 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3178. Min Act: -0.0000

Data Index: 374718 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1096872 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3239. Min Act: -0.0000

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1014118 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3401. Min Act: -0.0000

Data Index: 367272 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3325. Min Act: -0.0000

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3693. Min Act: -0.0000

Data Index: 116080 (C4 (Web Text))

Max Activating Token Index: 975