Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 851 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0802. Min Act: -0.0002

Data Index: 531051 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0643. Min Act: -0.0002

Data Index: 988643 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0613. Min Act: -0.0002

Data Index: 509861 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0579. Min Act: -0.0002

Data Index: 458119 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0572. Min Act: -0.0002

Data Index: 671482 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0568. Min Act: -0.0002

Data Index: 978527 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1170620 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0555. Min Act: -0.0002

Data Index: 932672 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0536. Min Act: -0.0002

Data Index: 937739 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1196559 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0526. Min Act: -0.0002

Data Index: 134570 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1061414 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0526. Min Act: -0.0002

Data Index: 421424 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0520. Min Act: -0.0002

Data Index: 954878 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0518. Min Act: -0.0002

Data Index: 331831 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1605666 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0509. Min Act: -0.0002

Data Index: 367442 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0508. Min Act: -0.0002

Data Index: 213258 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0507. Min Act: -0.0002

Data Index: 484284 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0496. Min Act: -0.0002

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 102