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

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

Neuron 3128 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: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0002

Data Index: 713824 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0591. Min Act: -0.0002

Data Index: 669272 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1137320 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1350750 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0592. Min Act: -0.0002

Data Index: 355649 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0607. Min Act: -0.0002

Data Index: 103030 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1356320 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0593. Min Act: -0.0002

Data Index: 208395 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1235749 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0562. Min Act: -0.0002

Data Index: 68512 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0514. Min Act: -0.0002

Data Index: 67456 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1033152 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1246757 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0538. Min Act: -0.0002

Data Index: 637809 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0496. Min Act: -0.0002

Data Index: 516851 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0524. Min Act: -0.0002

Data Index: 300409 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0529. Min Act: -0.0002

Data Index: 919924 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1043831 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0445. Min Act: -0.0002

Data Index: 784174 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1331806 (C4 (Web Text))

Max Activating Token Index: 445