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

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

Neuron 3398 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.6029. Min Act: -0.0000

Data Index: 447475 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.1132. Min Act: -0.0000

Data Index: 823213 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.1018. Min Act: -0.0000

Data Index: 1194278 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 3.6029. Min Range: -3.6029

Max Act: 3.0174. Min Act: -0.0000

Data Index: 684238 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.8023. Min Act: -0.0000

Data Index: 345207 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.4460. Min Act: -0.0000

Data Index: 331813 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.5490. Min Act: -0.0000

Data Index: 677360 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.5089. Min Act: -0.0000

Data Index: 1015601 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.4821. Min Act: -0.0000

Data Index: 429410 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.2770. Min Act: -0.0000

Data Index: 439521 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.2346. Min Act: -0.0000

Data Index: 159523 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.3343. Min Act: -0.0000

Data Index: 274101 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.4217. Min Act: -0.0000

Data Index: 1217628 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.1613. Min Act: -0.0000

Data Index: 785504 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.1506. Min Act: -0.0000

Data Index: 177926 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.3124. Min Act: -0.0000

Data Index: 358805 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.0611. Min Act: -0.0000

Data Index: 153664 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.2672. Min Act: -0.0000

Data Index: 174632 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.1425. Min Act: -0.0000

Data Index: 1251778 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 3.6029. Min Range: -3.6029

Max Act: 2.1499. Min Act: -0.0000

Data Index: 709576 (C4 (Web Text))

Max Activating Token Index: 475