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

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

Neuron 4490 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.6835. Min Act: -0.0000

Data Index: 164668 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.6279. Min Act: -0.0000

Data Index: 825371 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1032956 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5211. Min Act: -0.0000

Data Index: 171001 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5154. Min Act: -0.0000

Data Index: 687764 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4707. Min Act: -0.0000

Data Index: 812871 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4977. Min Act: -0.0000

Data Index: 360839 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1346553 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1202869 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4559. Min Act: 0.0000

Data Index: 290786 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4612. Min Act: -0.0000

Data Index: 869092 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1150211 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4668. Min Act: -0.0000

Data Index: 598202 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1075198 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4314. Min Act: 0.0000

Data Index: 311493 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1036762 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1200349 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4591. Min Act: -0.0000

Data Index: 2827 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1288764 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4470. Min Act: -0.0000

Data Index: 627722 (C4 (Web Text))

Max Activating Token Index: 614