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

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

Neuron 5263 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: 0.6727. Min Range: -0.6727

Max Act: 0.6727. Min Act: -0.0000

Data Index: 841915 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6283. Min Act: -0.0000

Data Index: 980758 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1267261 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4985. Min Act: -0.0000

Data Index: 616432 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5132. Min Act: -0.0000

Data Index: 323680 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4922. Min Act: -0.0000

Data Index: 903960 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5074. Min Act: -0.0000

Data Index: 151351 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5112. Min Act: -0.0000

Data Index: 173418 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1346674 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4692. Min Act: -0.0000

Data Index: 88045 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4488. Min Act: 0.0000

Data Index: 1215049 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1219190 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4586. Min Act: -0.0000

Data Index: 428608 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1023331 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4538. Min Act: -0.0000

Data Index: 180179 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4680. Min Act: -0.0000

Data Index: 578960 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4534. Min Act: -0.0000

Data Index: 373555 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4523. Min Act: 0.0000

Data Index: 320673 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4361. Min Act: -0.0000

Data Index: 674624 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4630. Min Act: -0.0000

Data Index: 630561 (C4 (Web Text))

Max Activating Token Index: 265