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

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

Neuron 944 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: 0.0682. Min Range: -0.0682

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1137360 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0656. Min Act: -0.0002

Data Index: 207701 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1191076 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0607. Min Act: -0.0002

Data Index: 538932 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0604. Min Act: -0.0002

Data Index: 952127 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1235210 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1273925 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0547. Min Act: -0.0002

Data Index: 808361 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0549. Min Act: -0.0002

Data Index: 594880 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0569. Min Act: -0.0002

Data Index: 105467 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0522. Min Act: -0.0002

Data Index: 980452 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1272240 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0500. Min Act: -0.0002

Data Index: 989646 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1131827 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0507. Min Act: -0.0002

Data Index: 82678 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0512. Min Act: -0.0002

Data Index: 684299 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0481. Min Act: -0.0002

Data Index: 588880 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1054050 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0506. Min Act: -0.0002

Data Index: 559586 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0471. Min Act: -0.0002

Data Index: 958553 (C4 (Web Text))

Max Activating Token Index: 359