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

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

Neuron 3802 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.7319. Min Act: -0.0002

Data Index: 1183034 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.7993. Min Act: -0.0002

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.7513. Min Act: -0.0002

Data Index: 1102456 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.6821. Min Act: -0.0002

Data Index: 925561 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.6791. Min Act: -0.0002

Data Index: 673875 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.5981. Min Act: -0.0002

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.5824. Min Act: -0.0002

Data Index: 158356 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.5516. Min Act: -0.0002

Data Index: 518419 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.4365. Min Act: -0.0002

Data Index: 585915 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.4562. Min Act: -0.0002

Data Index: 114413 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.5737. Min Act: -0.0002

Data Index: 22592 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.3954. Min Act: -0.0002

Data Index: 397343 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.4069. Min Act: -0.0002

Data Index: 1190801 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.4910. Min Act: -0.0002

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.3866. Min Act: -0.0002

Data Index: 199242 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.3639. Min Act: -0.0002

Data Index: 448883 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.3325. Min Act: -0.0002

Data Index: 171147 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.3089. Min Act: -0.0002

Data Index: 1240567 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.3828. Min Act: -0.0002

Data Index: 559166 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 1.7993. Min Range: -1.7993

Max Act: 1.3881. Min Act: -0.0002

Data Index: 1256522 (C4 (Web Text))

Max Activating Token Index: 298