Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 136 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1232. Min Act: -0.0003

Data Index: 432474 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1280595 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1130. Min Act: -0.0003

Data Index: 605385 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1231. Min Act: -0.0003

Data Index: 7199 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1146. Min Act: -0.0003

Data Index: 568429 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1126. Min Act: -0.0003

Data Index: 384811 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1067. Min Act: -0.0003

Data Index: 555742 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1071. Min Act: -0.0003

Data Index: 826478 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1001. Min Act: -0.0003

Data Index: 716959 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1059. Min Act: -0.0003

Data Index: 496285 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0977. Min Act: -0.0003

Data Index: 267019 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1028. Min Act: -0.0002

Data Index: 889485 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1000. Min Act: -0.0003

Data Index: 563335 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1025. Min Act: -0.0002

Data Index: 197636 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0998. Min Act: -0.0002

Data Index: 1341809 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0955. Min Act: -0.0003

Data Index: 599298 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0956. Min Act: -0.0003

Data Index: 232813 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0958. Min Act: -0.0003

Data Index: 590859 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0984. Min Act: -0.0003

Data Index: 964422 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1218226 (C4 (Web Text))

Max Activating Token Index: 867