Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.3585. Min Act: -0.0001

Data Index: 1063341 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0935. Min Act: -0.0001

Data Index: 157601 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.2773. Min Act: -0.0001

Data Index: 423376 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0562. Min Act: -0.0001

Data Index: 965311 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0523. Min Act: -0.0001

Data Index: 477488 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1251865 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0134. Min Act: -0.0001

Data Index: 363520 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.3585. Min Range: -1.3585

Max Act: 1.0512. Min Act: -0.0001

Data Index: 73274 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8983. Min Act: -0.0001

Data Index: 132002 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8848. Min Act: -0.0001

Data Index: 57342 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8984. Min Act: -0.0001

Data Index: 993337 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8395. Min Act: -0.0001

Data Index: 458792 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8117. Min Act: -0.0001

Data Index: 824100 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.9159. Min Act: -0.0001

Data Index: 411593 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8397. Min Act: -0.0001

Data Index: 1160103 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8795. Min Act: -0.0001

Data Index: 41699 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8235. Min Act: -0.0001

Data Index: 833913 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8169. Min Act: -0.0001

Data Index: 991506 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.7902. Min Act: -0.0001

Data Index: 975714 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.3585. Min Range: -1.3585

Max Act: 0.8566. Min Act: -0.0001

Data Index: 1572687 (Python Code)

Max Activating Token Index: 796