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

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

Neuron 3472 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.9184. Min Act: -0.0000

Data Index: 844789 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8791. Min Act: -0.0000

Data Index: 62075 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8007. Min Act: -0.0000

Data Index: 291100 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7553. Min Act: -0.0000

Data Index: 557444 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5958. Min Act: -0.0000

Data Index: 363186 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5901. Min Act: -0.0000

Data Index: 446534 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5667. Min Act: -0.0000

Data Index: 595189 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5637. Min Act: -0.0000

Data Index: 519669 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5832. Min Act: -0.0000

Data Index: 402457 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5585. Min Act: -0.0000

Data Index: 618255 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5226. Min Act: 0.0000

Data Index: 106945 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5331. Min Act: -0.0000

Data Index: 348528 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1186434 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.4983. Min Act: -0.0000

Data Index: 984978 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.4833. Min Act: -0.0000

Data Index: 870470 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1359344 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.4787. Min Act: -0.0000

Data Index: 183359 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.4527. Min Act: -0.0000

Data Index: 205924 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.4674. Min Act: -0.0000

Data Index: 233769 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.4437. Min Act: -0.0000

Data Index: 246029 (C4 (Web Text))

Max Activating Token Index: 218