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

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

Neuron 2154 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6755. Min Act: -0.0002

Data Index: 15123 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6246. Min Act: -0.0002

Data Index: 1084755 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6170. Min Act: -0.0002

Data Index: 583410 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5963. Min Act: -0.0003

Data Index: 696722 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5662. Min Act: -0.0002

Data Index: 307147 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5608. Min Act: -0.0002

Data Index: 976275 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5383. Min Act: -0.0003

Data Index: 1339672 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5524. Min Act: -0.0002

Data Index: 1027703 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5705. Min Act: -0.0002

Data Index: 758860 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5503. Min Act: -0.0003

Data Index: 1354784 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5424. Min Act: -0.0002

Data Index: 756683 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5377. Min Act: -0.0003

Data Index: 1078140 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5361. Min Act: -0.0002

Data Index: 186984 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5187. Min Act: -0.0002

Data Index: 1187309 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5347. Min Act: -0.0002

Data Index: 1314986 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5327. Min Act: -0.0003

Data Index: 426320 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5486. Min Act: -0.0002

Data Index: 1231778 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5220. Min Act: -0.0002

Data Index: 1224104 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5030. Min Act: -0.0002

Data Index: 89509 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5183. Min Act: -0.0002

Data Index: 517970 (C4 (Web Text))

Max Activating Token Index: 874