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

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

Neuron 5190 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9910. Min Act: -0.0001

Data Index: 1326459 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8470. Min Act: -0.0001

Data Index: 907188 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9154. Min Act: -0.0001

Data Index: 188365 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8311. Min Act: -0.0001

Data Index: 543301 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9321. Min Act: -0.0001

Data Index: 1173210 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9006. Min Act: -0.0001

Data Index: 725155 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8489. Min Act: -0.0001

Data Index: 1062516 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8852. Min Act: -0.0001

Data Index: 757041 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8483. Min Act: -0.0001

Data Index: 604697 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1276390 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7205. Min Act: -0.0001

Data Index: 1004049 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8071. Min Act: -0.0001

Data Index: 163928 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8742. Min Act: -0.0001

Data Index: 893931 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7758. Min Act: -0.0001

Data Index: 318127 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7638. Min Act: -0.0001

Data Index: 1032632 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7911. Min Act: -0.0001

Data Index: 1000502 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8612. Min Act: -0.0001

Data Index: 639573 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8553. Min Act: -0.0001

Data Index: 723768 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8545. Min Act: -0.0001

Data Index: 539548 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8679. Min Act: -0.0001

Data Index: 1111463 (C4 (Web Text))

Max Activating Token Index: 263