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

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

Neuron 653 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0939. Min Range: -3.0939

Max Act: 3.0939. Min Act: -0.0000

Data Index: 817841 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.6002. Min Act: -0.0000

Data Index: 1096360 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.5674. Min Act: -0.0000

Data Index: 555115 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.6900. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.5383. Min Act: -0.0000

Data Index: 958538 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.5543. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.4850. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.4559. Min Act: -0.0000

Data Index: 1286877 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.4504. Min Act: -0.0000

Data Index: 103301 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.5108. Min Act: -0.0000

Data Index: 845875 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.3403. Min Act: -0.0000

Data Index: 817242 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.3373. Min Act: -0.0000

Data Index: 577629 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.2073. Min Act: -0.0000

Data Index: 859075 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.3031. Min Act: -0.0000

Data Index: 786575 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.2140. Min Act: -0.0000

Data Index: 978006 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1327427 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.0674. Min Act: -0.0000

Data Index: 68594 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.0598. Min Act: -0.0000

Data Index: 944869 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.1359. Min Act: -0.0000

Data Index: 402247 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 3.0939. Min Range: -3.0939

Max Act: 2.1358. Min Act: -0.0000

Data Index: 606741 (C4 (Web Text))

Max Activating Token Index: 106