Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1979 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.9343. Min Act: -0.0001

Data Index: 355555 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8668. Min Act: -0.0001

Data Index: 783332 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8086. Min Act: -0.0000

Data Index: 634638 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6632. Min Act: -0.0001

Data Index: 391432 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6507. Min Act: -0.0001

Data Index: 126708 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6041. Min Act: -0.0001

Data Index: 87402 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6012. Min Act: -0.0000

Data Index: 905150 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5845. Min Act: -0.0001

Data Index: 530661 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5815. Min Act: -0.0001

Data Index: 1328148 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5981. Min Act: -0.0000

Data Index: 903037 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6178. Min Act: -0.0000

Data Index: 670948 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6142. Min Act: -0.0001

Data Index: 393051 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6701. Min Act: -0.0001

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5895. Min Act: -0.0001

Data Index: 500824 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1174138 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5888. Min Act: -0.0001

Data Index: 616070 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1276385 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1315394 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5678. Min Act: -0.0000

Data Index: 313601 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.5459. Min Act: -0.0001

Data Index: 29204 (C4 (Web Text))

Max Activating Token Index: 288