Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1492 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0006

Data Index: 383780 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0661. Min Act: -0.0006

Data Index: 796118 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0687. Min Act: -0.0006

Data Index: 1153529 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0654. Min Act: -0.0006

Data Index: 155924 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0636. Min Act: -0.0006

Data Index: 768447 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0658. Min Act: -0.0006

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0657. Min Act: -0.0006

Data Index: 1192771 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0629. Min Act: -0.0006

Data Index: 479415 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0621. Min Act: -0.0006

Data Index: 1309630 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0635. Min Act: -0.0006

Data Index: 815056 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0630. Min Act: -0.0006

Data Index: 674600 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0624. Min Act: -0.0006

Data Index: 1088240 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0540. Min Act: -0.0006

Data Index: 85634 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0562. Min Act: -0.0006

Data Index: 1163273 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0537. Min Act: -0.0006

Data Index: 341050 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0584. Min Act: -0.0006

Data Index: 606135 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0531. Min Act: -0.0006

Data Index: 1201621 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0569. Min Act: -0.0006

Data Index: 932577 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0546. Min Act: -0.0006

Data Index: 130157 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0565. Min Act: -0.0006

Data Index: 655990 (C4 (Web Text))

Max Activating Token Index: 239