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

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

Neuron 4272 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1863. Min Range: -4.1863

Max Act: 4.1863. Min Act: -0.0000

Data Index: 420537 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.6778. Min Act: -0.0000

Data Index: 305812 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.7080. Min Act: -0.0000

Data Index: 41401 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.7139. Min Act: -0.0000

Data Index: 149503 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.4795. Min Act: -0.0000

Data Index: 774095 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.6325. Min Act: -0.0000

Data Index: 591568 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.5778. Min Act: -0.0000

Data Index: 935521 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.4531. Min Act: -0.0000

Data Index: 1323782 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.4687. Min Act: -0.0000

Data Index: 1260632 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.5736. Min Act: -0.0000

Data Index: 155936 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.5906. Min Act: -0.0000

Data Index: 952848 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.4419. Min Act: -0.0000

Data Index: 1335386 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.4247. Min Act: -0.0000

Data Index: 1123363 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.5252. Min Act: -0.0000

Data Index: 392327 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.5042. Min Act: -0.0000

Data Index: 704964 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.2474. Min Act: -0.0000

Data Index: 451109 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.5518. Min Act: -0.0000

Data Index: 719739 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.2488. Min Act: -0.0000

Data Index: 526005 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.2323. Min Act: -0.0000

Data Index: 392046 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 4.1863. Min Range: -4.1863

Max Act: 2.2015. Min Act: -0.0000

Data Index: 124618 (C4 (Web Text))

Max Activating Token Index: 225