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

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

Neuron 1944 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: 0.3517. Min Range: -0.3517

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1544457 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3221. Min Act: -0.0000

Data Index: 482625 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1420008 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3043. Min Act: -0.0000

Data Index: 315711 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1615337 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1382428 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3189. Min Act: -0.0000

Data Index: 370582 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1062868 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1004487 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1275942 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2854. Min Act: -0.0000

Data Index: 353934 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3086. Min Act: -0.0000

Data Index: 504813 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1111081 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2736. Min Act: -0.0000

Data Index: 818269 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1161028 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1616518 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1166392 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1508671 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2716. Min Act: -0.0000

Data Index: 723289 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.3517. Min Range: -0.3517

Max Act: 0.2701. Min Act: -0.0000

Data Index: 830692 (C4 (Web Text))

Max Activating Token Index: 810