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

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

Neuron 5205 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.8977. Min Act: -0.0000

Data Index: 157663 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 5.0864. Min Range: -5.0864

Max Act: 5.0644. Min Act: -0.0000

Data Index: 570610 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 5.0864. Min Range: -5.0864

Max Act: 5.0864. Min Act: -0.0000

Data Index: 320983 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.9496. Min Act: -0.0000

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.7602. Min Act: -0.0000

Data Index: 420041 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.7420. Min Act: -0.0000

Data Index: 866397 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.3324. Min Act: -0.0000

Data Index: 614512 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.3844. Min Act: -0.0000

Data Index: 23928 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.3773. Min Act: -0.0000

Data Index: 6645 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.3868. Min Act: -0.0000

Data Index: 443752 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.0180. Min Act: -0.0000

Data Index: 193716 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.3283. Min Act: -0.0000

Data Index: 878769 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.2844. Min Act: -0.0000

Data Index: 880603 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.1711. Min Act: -0.0000

Data Index: 1198998 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.1432. Min Act: -0.0000

Data Index: 342391 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 5.0864. Min Range: -5.0864

Max Act: 3.8935. Min Act: -0.0000

Data Index: 244389 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.2503. Min Act: -0.0000

Data Index: 1158433 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 5.0864. Min Range: -5.0864

Max Act: 4.0315. Min Act: -0.0000

Data Index: 1175080 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 5.0864. Min Range: -5.0864

Max Act: 3.9534. Min Act: -0.0000

Data Index: 1322888 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 5.0864. Min Range: -5.0864

Max Act: 3.9134. Min Act: -0.0000

Data Index: 910504 (C4 (Web Text))

Max Activating Token Index: 98