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

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

Neuron 2029 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0726. Min Act: -0.0006

Data Index: 64304 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0677. Min Act: -0.0006

Data Index: 1335455 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0676. Min Act: -0.0006

Data Index: 905797 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0606. Min Act: -0.0006

Data Index: 969791 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0598. Min Act: -0.0006

Data Index: 607960 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0628. Min Act: -0.0006

Data Index: 886838 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0592. Min Act: -0.0006

Data Index: 678979 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0566. Min Act: -0.0006

Data Index: 435824 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0567. Min Act: -0.0006

Data Index: 1354026 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0586. Min Act: -0.0006

Data Index: 314475 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0560. Min Act: -0.0006

Data Index: 1087014 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0557. Min Act: -0.0006

Data Index: 459987 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0579. Min Act: -0.0006

Data Index: 479882 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0553. Min Act: -0.0006

Data Index: 426519 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0577. Min Act: -0.0006

Data Index: 1059215 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0554. Min Act: -0.0006

Data Index: 489362 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0546. Min Act: -0.0006

Data Index: 859306 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0544. Min Act: -0.0006

Data Index: 1097241 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0542. Min Act: -0.0006

Data Index: 98165 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0565. Min Act: -0.0006

Data Index: 853105 (C4 (Web Text))

Max Activating Token Index: 540