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

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

Neuron 900 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: 0.6229. Min Range: -0.6229

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1287246 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1452830 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4474. Min Act: -0.0000

Data Index: 184085 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1139365 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3878. Min Act: -0.0000

Data Index: 761748 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3952. Min Act: -0.0000

Data Index: 656509 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4136. Min Act: -0.0000

Data Index: 822811 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1024065 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4136. Min Act: -0.0000

Data Index: 799926 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3842. Min Act: -0.0000

Data Index: 942888 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3617. Min Act: -0.0000

Data Index: 628654 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1299003 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1556244 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3484. Min Act: -0.0000

Data Index: 766971 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3654. Min Act: -0.0000

Data Index: 578321 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1250371 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3442. Min Act: -0.0000

Data Index: 650305 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3534. Min Act: -0.0000

Data Index: 760227 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1561276 (Python Code)

Max Activating Token Index: 266

Text #19

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.3227. Min Act: -0.0000

Data Index: 255927 (C4 (Web Text))

Max Activating Token Index: 37