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

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

Neuron 949 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: 2.7335. Min Range: -2.7335

Max Act: 2.7335. Min Act: -0.0000

Data Index: 261526 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.5870. Min Act: -0.0000

Data Index: 706813 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.3116. Min Act: -0.0000

Data Index: 514120 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.2606. Min Act: -0.0000

Data Index: 945936 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.1553. Min Act: -0.0000

Data Index: 479388 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.0138. Min Act: -0.0000

Data Index: 810893 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.1240. Min Act: -0.0000

Data Index: 1201747 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.1169. Min Act: -0.0000

Data Index: 1249148 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.1242. Min Act: -0.0000

Data Index: 1070267 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.0714. Min Act: -0.0000

Data Index: 231146 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.0427. Min Act: -0.0000

Data Index: 10944 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.0365. Min Act: -0.0000

Data Index: 990040 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 2.7335. Min Range: -2.7335

Max Act: 2.0077. Min Act: -0.0000

Data Index: 624821 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 2.7335. Min Range: -2.7335

Max Act: 1.8771. Min Act: -0.0000

Data Index: 1200040 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 2.7335. Min Range: -2.7335

Max Act: 1.9554. Min Act: -0.0000

Data Index: 774038 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 2.7335. Min Range: -2.7335

Max Act: 1.9765. Min Act: -0.0000

Data Index: 1139941 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 2.7335. Min Range: -2.7335

Max Act: 1.9809. Min Act: -0.0000

Data Index: 428923 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 2.7335. Min Range: -2.7335

Max Act: 1.9553. Min Act: -0.0000

Data Index: 837924 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 2.7335. Min Range: -2.7335

Max Act: 1.8599. Min Act: -0.0000

Data Index: 1216623 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 2.7335. Min Range: -2.7335

Max Act: 1.9487. Min Act: -0.0000

Data Index: 47451 (C4 (Web Text))

Max Activating Token Index: 130