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

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

Neuron 3999 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.3200. Min Act: -0.0000

Data Index: 768486 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.2160. Min Act: -0.0000

Data Index: 819981 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.2314. Min Act: -0.0000

Data Index: 664036 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.1471. Min Act: -0.0000

Data Index: 340438 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1290905 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1155934 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9500. Min Act: -0.0000

Data Index: 437489 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.8917. Min Act: -0.0000

Data Index: 980468 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9480. Min Act: -0.0000

Data Index: 78478 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.8997. Min Act: -0.0000

Data Index: 76825 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9595. Min Act: -0.0000

Data Index: 368847 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9074. Min Act: -0.0000

Data Index: 270012 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.8755. Min Act: -0.0000

Data Index: 8772 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9013. Min Act: -0.0000

Data Index: 868693 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.8367. Min Act: -0.0000

Data Index: 384931 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1175337 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9318. Min Act: -0.0000

Data Index: 503173 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.8738. Min Act: -0.0000

Data Index: 515504 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.8631. Min Act: -0.0000

Data Index: 178654 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9225. Min Act: -0.0000

Data Index: 960220 (C4 (Web Text))

Max Activating Token Index: 604