Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 628 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.6923. Min Act: -0.0001

Data Index: 245045 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.5938. Min Act: -0.0001

Data Index: 1072073 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.6160. Min Act: -0.0001

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4328. Min Act: -0.0001

Data Index: 298523 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4617. Min Act: -0.0001

Data Index: 662182 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4856. Min Act: -0.0000

Data Index: 613293 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4636. Min Act: -0.0001

Data Index: 1177847 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3376. Min Act: -0.0001

Data Index: 1029000 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3537. Min Act: -0.0001

Data Index: 526607 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3949. Min Act: -0.0001

Data Index: 830739 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3044. Min Act: -0.0001

Data Index: 999651 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.4061. Min Act: -0.0001

Data Index: 1118227 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3574. Min Act: -0.0001

Data Index: 1063598 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2290. Min Act: -0.0001

Data Index: 170367 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2928. Min Act: -0.0001

Data Index: 1237360 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3241. Min Act: -0.0001

Data Index: 172336 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.3613. Min Act: -0.0001

Data Index: 395596 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2599. Min Act: -0.0001

Data Index: 500839 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2984. Min Act: -0.0001

Data Index: 1344738 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.6923. Min Range: -1.6923

Max Act: 1.2635. Min Act: -0.0001

Data Index: 1023929 (C4 (Web Text))

Max Activating Token Index: 763