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

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

Neuron 2373 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.7527. Min Act: -0.0002

Data Index: 654752 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6951. Min Act: -0.0002

Data Index: 474258 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5951. Min Act: -0.0002

Data Index: 316306 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6808. Min Act: -0.0002

Data Index: 1100147 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6407. Min Act: -0.0002

Data Index: 169589 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6587. Min Act: -0.0002

Data Index: 983108 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6392. Min Act: -0.0002

Data Index: 75321 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6735. Min Act: -0.0002

Data Index: 475913 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6129. Min Act: -0.0002

Data Index: 558829 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6118. Min Act: -0.0002

Data Index: 767803 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6052. Min Act: -0.0002

Data Index: 1031917 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6381. Min Act: -0.0002

Data Index: 415451 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6244. Min Act: -0.0002

Data Index: 6509 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5812. Min Act: -0.0002

Data Index: 64404 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5653. Min Act: -0.0002

Data Index: 622452 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6326. Min Act: -0.0002

Data Index: 1260471 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6157. Min Act: -0.0002

Data Index: 703601 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6320. Min Act: -0.0002

Data Index: 41444 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.5693. Min Act: -0.0002

Data Index: 969952 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.7527. Min Range: -0.7527

Max Act: 0.6083. Min Act: -0.0002

Data Index: 301467 (C4 (Web Text))

Max Activating Token Index: 187