Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 8 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0002

Data Index: 804068 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0664. Min Act: -0.0002

Data Index: 86138 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0663. Min Act: -0.0002

Data Index: 958873 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0591. Min Act: -0.0002

Data Index: 319798 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0493. Min Act: -0.0002

Data Index: 221904 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0574. Min Act: -0.0002

Data Index: 850825 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0599. Min Act: -0.0002

Data Index: 970215 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1162642 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0560. Min Act: -0.0002

Data Index: 715985 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1050354 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1201722 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0536. Min Act: -0.0002

Data Index: 733934 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1207898 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1358441 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1093727 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0576. Min Act: -0.0002

Data Index: 328919 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1094799 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1210070 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1109375 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0542. Min Act: -0.0002

Data Index: 452491 (C4 (Web Text))

Max Activating Token Index: 23