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

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

Neuron 2764 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: 0.5759. Min Range: -0.5759

Max Act: 0.5759. Min Act: -0.0002

Data Index: 876314 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5592. Min Act: -0.0002

Data Index: 624123 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5185. Min Act: -0.0002

Data Index: 260765 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5649. Min Act: -0.0002

Data Index: 57334 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4672. Min Act: -0.0002

Data Index: 492676 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4968. Min Act: -0.0002

Data Index: 868602 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4607. Min Act: -0.0002

Data Index: 1124702 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5151. Min Act: -0.0002

Data Index: 210038 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4814. Min Act: -0.0002

Data Index: 396009 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4380. Min Act: -0.0002

Data Index: 836618 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4520. Min Act: -0.0002

Data Index: 396421 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4499. Min Act: -0.0002

Data Index: 153106 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5279. Min Act: -0.0002

Data Index: 128624 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4702. Min Act: -0.0002

Data Index: 858972 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4324. Min Act: -0.0002

Data Index: 430375 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4100. Min Act: -0.0002

Data Index: 117894 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4495. Min Act: -0.0002

Data Index: 1109919 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4550. Min Act: -0.0002

Data Index: 314607 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3799. Min Act: -0.0002

Data Index: 218568 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4204. Min Act: -0.0002

Data Index: 1231874 (C4 (Web Text))

Max Activating Token Index: 768