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

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

Neuron 5082 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.5059. Min Act: -0.0000

Data Index: 728889 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1544 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1132083 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1333037 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1188010 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3816. Min Act: -0.0000

Data Index: 590106 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4091. Min Act: -0.0000

Data Index: 901063 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1334782 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1359081 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1184588 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3741. Min Act: -0.0000

Data Index: 527305 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3725. Min Act: -0.0000

Data Index: 707665 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3431. Min Act: -0.0000

Data Index: 909886 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3548. Min Act: -0.0000

Data Index: 385340 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3741. Min Act: -0.0000

Data Index: 766859 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1007121 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3578. Min Act: -0.0000

Data Index: 882364 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1295953 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3415. Min Act: -0.0000

Data Index: 151458 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3406. Min Act: -0.0000

Data Index: 385709 (C4 (Web Text))

Max Activating Token Index: 360