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

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

Neuron 840 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0002

Data Index: 941878 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0662. Min Act: -0.0003

Data Index: 1053677 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0658. Min Act: -0.0002

Data Index: 161206 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0631. Min Act: -0.0003

Data Index: 76327 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0611. Min Act: -0.0002

Data Index: 315919 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1284263 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0605. Min Act: -0.0002

Data Index: 729049 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0609. Min Act: -0.0002

Data Index: 99713 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0611. Min Act: -0.0003

Data Index: 360392 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0596. Min Act: -0.0002

Data Index: 500895 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0585. Min Act: -0.0002

Data Index: 747803 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1133182 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0595. Min Act: -0.0002

Data Index: 965316 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0593. Min Act: -0.0002

Data Index: 31443 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1228564 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0563. Min Act: -0.0002

Data Index: 540074 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0593. Min Act: -0.0002

Data Index: 999348 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0561. Min Act: -0.0003

Data Index: 501813 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1179415 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0561. Min Act: -0.0002

Data Index: 40049 (C4 (Web Text))

Max Activating Token Index: 569