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

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

Neuron 60 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: 0.6596. Min Range: -0.6596

Max Act: 0.6596. Min Act: -0.0000

Data Index: 427482 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.6454. Min Act: -0.0000

Data Index: 216594 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5896. Min Act: -0.0000

Data Index: 516900 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1123327 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1042121 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1129075 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5149. Min Act: 0.0000

Data Index: 1255792 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4790. Min Act: -0.0000

Data Index: 927353 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5147. Min Act: -0.0000

Data Index: 628384 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1194639 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4707. Min Act: 0.0001

Data Index: 869348 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1021135 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4311. Min Act: -0.0000

Data Index: 539418 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4534. Min Act: -0.0000

Data Index: 354779 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4560. Min Act: -0.0000

Data Index: 597008 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4141. Min Act: -0.0000

Data Index: 482276 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4204. Min Act: -0.0000

Data Index: 904801 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4176. Min Act: -0.0000

Data Index: 708223 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1273665 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.6596. Min Range: -0.6596

Max Act: 0.4320. Min Act: -0.0000

Data Index: 741633 (C4 (Web Text))

Max Activating Token Index: 684