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

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

Neuron 1631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0631. Min Act: -0.0002

Data Index: 84004 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0633. Min Act: -0.0003

Data Index: 547806 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0003

Data Index: 257928 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0582. Min Act: -0.0003

Data Index: 805961 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1312003 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0593. Min Act: -0.0003

Data Index: 964920 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1001759 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0580. Min Act: -0.0003

Data Index: 999279 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0577. Min Act: -0.0003

Data Index: 169441 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0557. Min Act: -0.0003

Data Index: 544670 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0574. Min Act: -0.0003

Data Index: 227938 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1171884 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0567. Min Act: -0.0003

Data Index: 814429 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0517. Min Act: -0.0002

Data Index: 797542 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1312138 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0518. Min Act: -0.0003

Data Index: 671532 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0520. Min Act: -0.0003

Data Index: 720203 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1163681 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1149790 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1101514 (C4 (Web Text))

Max Activating Token Index: 76