Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 677 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0668. Min Act: -0.0001

Data Index: 998004 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0001

Data Index: 510275 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0633. Min Act: -0.0001

Data Index: 33076 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0585. Min Act: -0.0001

Data Index: 298762 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1022374 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1115617 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0513. Min Act: -0.0001

Data Index: 995326 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0536. Min Act: -0.0001

Data Index: 694766 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0493. Min Act: -0.0001

Data Index: 1276283 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0528. Min Act: -0.0001

Data Index: 932535 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1082562 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0505. Min Act: -0.0001

Data Index: 368808 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0540. Min Act: -0.0001

Data Index: 780950 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0547. Min Act: -0.0001

Data Index: 378750 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0520. Min Act: -0.0001

Data Index: 630975 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0523. Min Act: -0.0001

Data Index: 96655 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0507. Min Act: -0.0001

Data Index: 672844 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0530. Min Act: -0.0001

Data Index: 854870 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0529. Min Act: -0.0001

Data Index: 271910 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1049709 (C4 (Web Text))

Max Activating Token Index: 874