Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3871 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0539. Min Range: -1.0539

Max Act: 1.0539. Min Act: -0.0000

Data Index: 6728 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1260148 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 1.0539. Min Range: -1.0539

Max Act: 1.0046. Min Act: -0.0000

Data Index: 1147256 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.9701. Min Act: -0.0000

Data Index: 544250 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.9376. Min Act: -0.0001

Data Index: 504336 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8223. Min Act: -0.0000

Data Index: 436337 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8726. Min Act: -0.0000

Data Index: 72021 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8142. Min Act: -0.0000

Data Index: 842785 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1106776 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8369. Min Act: -0.0001

Data Index: 353949 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8106. Min Act: -0.0000

Data Index: 415803 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1132021 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8165. Min Act: -0.0000

Data Index: 970583 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8443. Min Act: 0.0000

Data Index: 1166538 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1184212 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.7938. Min Act: -0.0000

Data Index: 30780 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1009003 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.7494. Min Act: -0.0000

Data Index: 535467 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1229123 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.8234. Min Act: 0.0000

Data Index: 903033 (C4 (Web Text))

Max Activating Token Index: 818