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

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

Neuron 380 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6037. Min Range: -4.6037

Max Act: 4.6037. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.9886. Min Act: -0.0000

Data Index: 1334252 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.8400. Min Act: -0.0000

Data Index: 851948 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.7435. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.3993. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.1652. Min Act: -0.0000

Data Index: 655429 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.1457. Min Act: -0.0000

Data Index: 346867 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.1463. Min Act: -0.0000

Data Index: 617599 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.9905. Min Act: -0.0000

Data Index: 139060 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.2550. Min Act: -0.0000

Data Index: 453124 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.0311. Min Act: -0.0000

Data Index: 450551 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 4.6037. Min Range: -4.6037

Max Act: 3.0023. Min Act: -0.0000

Data Index: 443812 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.9956. Min Act: -0.0000

Data Index: 209379 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.9214. Min Act: -0.0000

Data Index: 989544 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.7685. Min Act: -0.0000

Data Index: 553733 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.7459. Min Act: -0.0000

Data Index: 202688 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.7043. Min Act: -0.0000

Data Index: 697333 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.8135. Min Act: -0.0000

Data Index: 1256847 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.6896. Min Act: -0.0000

Data Index: 963915 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 4.6037. Min Range: -4.6037

Max Act: 2.8066. Min Act: -0.0000

Data Index: 29301 (C4 (Web Text))

Max Activating Token Index: 466