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

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

Neuron 2206 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.6786. Min Act: -0.0003

Data Index: 1039465 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.6680. Min Act: -0.0003

Data Index: 1090061 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.6184. Min Act: -0.0003

Data Index: 187029 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5919. Min Act: -0.0003

Data Index: 723982 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5878. Min Act: -0.0003

Data Index: 326630 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5853. Min Act: -0.0003

Data Index: 950638 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5965. Min Act: -0.0003

Data Index: 599106 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.6037. Min Act: -0.0003

Data Index: 776239 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5985. Min Act: -0.0003

Data Index: 1080093 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5620. Min Act: -0.0003

Data Index: 1091056 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5408. Min Act: -0.0003

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5764. Min Act: -0.0003

Data Index: 374170 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5663. Min Act: -0.0003

Data Index: 965602 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5678. Min Act: -0.0003

Data Index: 423997 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5460. Min Act: -0.0003

Data Index: 648571 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5438. Min Act: -0.0003

Data Index: 1141543 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5533. Min Act: -0.0003

Data Index: 367903 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5516. Min Act: -0.0003

Data Index: 1189156 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5331. Min Act: -0.0004

Data Index: 1075791 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.6786. Min Range: -0.6786

Max Act: 0.5496. Min Act: -0.0003

Data Index: 1226194 (C4 (Web Text))

Max Activating Token Index: 183