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

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

Neuron 2940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.3526. Min Act: -0.0000

Data Index: 98083 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.1377. Min Act: -0.0000

Data Index: 578966 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.1562. Min Act: -0.0000

Data Index: 384310 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1058331 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0550. Min Act: -0.0000

Data Index: 950120 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0028. Min Act: -0.0000

Data Index: 681707 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9906. Min Act: -0.0000

Data Index: 419749 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9802. Min Act: -0.0000

Data Index: 732584 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1284263 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0046. Min Act: -0.0000

Data Index: 426688 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9689. Min Act: -0.0001

Data Index: 513217 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0251. Min Act: -0.0000

Data Index: 726362 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9610. Min Act: -0.0000

Data Index: 692023 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.3526. Min Range: -1.3526

Max Act: 1.0259. Min Act: -0.0000

Data Index: 613991 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9567. Min Act: -0.0000

Data Index: 651553 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9686. Min Act: -0.0000

Data Index: 212942 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.8986. Min Act: -0.0000

Data Index: 842368 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9674. Min Act: -0.0000

Data Index: 737688 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9445. Min Act: -0.0000

Data Index: 126463 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.3526. Min Range: -1.3526

Max Act: 0.9304. Min Act: -0.0000

Data Index: 480572 (C4 (Web Text))

Max Activating Token Index: 380