Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 663 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0585. Min Range: -1.0585

Max Act: 1.0090. Min Act: -0.0001

Data Index: 1103703 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.0585. Min Range: -1.0585

Max Act: 1.0585. Min Act: -0.0001

Data Index: 166370 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 1.0585. Min Range: -1.0585

Max Act: 1.0240. Min Act: -0.0001

Data Index: 514093 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8516. Min Act: -0.0001

Data Index: 755509 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8318. Min Act: -0.0001

Data Index: 768252 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8243. Min Act: -0.0001

Data Index: 589254 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8362. Min Act: -0.0001

Data Index: 194720 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8570. Min Act: -0.0001

Data Index: 1462765 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7698. Min Act: -0.0001

Data Index: 244828 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7944. Min Act: -0.0001

Data Index: 1149842 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8075. Min Act: -0.0001

Data Index: 131103 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7822. Min Act: -0.0001

Data Index: 95639 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7985. Min Act: -0.0001

Data Index: 1592490 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7623. Min Act: -0.0001

Data Index: 435226 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7789. Min Act: -0.0001

Data Index: 1308725 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7453. Min Act: -0.0001

Data Index: 907798 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8046. Min Act: -0.0001

Data Index: 158892 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7380. Min Act: -0.0001

Data Index: 516648 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7418. Min Act: -0.0001

Data Index: 366479 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7422. Min Act: -0.0001

Data Index: 1221727 (C4 (Web Text))

Max Activating Token Index: 635