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

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

Neuron 425 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.8057. Min Act: -0.0000

Data Index: 868023 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.7332. Min Act: -0.0000

Data Index: 438623 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1160518 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5303. Min Act: -0.0000

Data Index: 254568 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1001520 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5328. Min Act: -0.0000

Data Index: 525195 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1210900 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1146817 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5327. Min Act: -0.0000

Data Index: 593770 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5112. Min Act: -0.0000

Data Index: 947554 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5008. Min Act: -0.0000

Data Index: 306367 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5033. Min Act: -0.0000

Data Index: 267339 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4881. Min Act: -0.0000

Data Index: 342132 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4607. Min Act: -0.0000

Data Index: 486780 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4694. Min Act: -0.0000

Data Index: 283143 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1329012 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4751. Min Act: -0.0000

Data Index: 71316 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4382. Min Act: -0.0000

Data Index: 227596 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1212437 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4497. Min Act: -0.0000

Data Index: 433443 (C4 (Web Text))

Max Activating Token Index: 944