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

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

Neuron 2952 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.4320. Min Act: -0.0000

Data Index: 420728 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3881. Min Act: -0.0000

Data Index: 844061 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1586. Min Act: -0.0000

Data Index: 523823 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1323. Min Act: -0.0000

Data Index: 915478 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0689. Min Act: -0.0000

Data Index: 417756 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1065. Min Act: -0.0000

Data Index: 797410 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.9630. Min Act: -0.0000

Data Index: 87052 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8874. Min Act: -0.0000

Data Index: 517491 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1345136 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1042581 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.7590. Min Act: -0.0000

Data Index: 479463 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.7861. Min Act: -0.0000

Data Index: 100997 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1297394 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.7880. Min Act: -0.0000

Data Index: 196341 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.7668. Min Act: -0.0000

Data Index: 585637 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1315770 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.8067. Min Act: -0.0000

Data Index: 343651 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.7482. Min Act: -0.0000

Data Index: 610454 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.7707. Min Act: -0.0000

Data Index: 173414 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.7272. Min Act: -0.0000

Data Index: 67905 (C4 (Web Text))

Max Activating Token Index: 627