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

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

Neuron 653 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1051086 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6923. Min Act: -0.0000

Data Index: 344316 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5980. Min Act: -0.0000

Data Index: 604810 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5516. Min Act: -0.0000

Data Index: 266447 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5768. Min Act: -0.0000

Data Index: 344269 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1277249 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5213. Min Act: -0.0000

Data Index: 448453 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1018883 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5397. Min Act: -0.0000

Data Index: 494824 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1344678 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5040. Min Act: -0.0000

Data Index: 574508 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4714. Min Act: -0.0000

Data Index: 836491 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1156006 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4324. Min Act: -0.0000

Data Index: 837332 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1112294 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4790. Min Act: -0.0000

Data Index: 706471 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1277068 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1092926 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1248202 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4185. Min Act: -0.0000

Data Index: 556402 (C4 (Web Text))

Max Activating Token Index: 943