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

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

Neuron 2752 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.6802. Min Act: -0.0000

Data Index: 612410 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1001251 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1315343 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5711. Min Act: -0.0000

Data Index: 733752 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5635. Min Act: -0.0000

Data Index: 444392 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5214. Min Act: -0.0000

Data Index: 637235 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5308. Min Act: -0.0000

Data Index: 764553 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5240. Min Act: -0.0000

Data Index: 689157 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5247. Min Act: -0.0000

Data Index: 562816 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5167. Min Act: -0.0000

Data Index: 631511 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5010. Min Act: -0.0000

Data Index: 29639 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.5043. Min Act: -0.0000

Data Index: 428670 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1210932 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1091110 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4699. Min Act: -0.0000

Data Index: 188236 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4856. Min Act: -0.0000

Data Index: 683676 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4652. Min Act: -0.0000

Data Index: 4514 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4613. Min Act: -0.0000

Data Index: 346341 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1180456 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.6802. Min Range: -0.6802

Max Act: 0.4764. Min Act: -0.0000

Data Index: 838158 (C4 (Web Text))

Max Activating Token Index: 810