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

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

Neuron 2016 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: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0001

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0656. Min Act: -0.0001

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0624. Min Act: -0.0001

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0621. Min Act: -0.0000

Data Index: 33491 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0598. Min Act: -0.0002

Data Index: 637225 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0599. Min Act: -0.0002

Data Index: 866673 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0584. Min Act: -0.0000

Data Index: 382590 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0589. Min Act: -0.0001

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1286735 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0575. Min Act: -0.0001

Data Index: 959694 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0565. Min Act: -0.0001

Data Index: 896920 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0573. Min Act: -0.0001

Data Index: 115109 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1244466 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0575. Min Act: -0.0001

Data Index: 466663 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0575. Min Act: -0.0001

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1124108 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1184169 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1137510 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1169283 (C4 (Web Text))

Max Activating Token Index: 792