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

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

Neuron 3307 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: 0.5786. Min Range: -0.5786

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1227872 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1197834 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4719. Min Act: -0.0000

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4624. Min Act: -0.0000

Data Index: 275260 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4661. Min Act: -0.0000

Data Index: 863618 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4499. Min Act: -0.0000

Data Index: 950336 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4516. Min Act: -0.0000

Data Index: 681260 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4296. Min Act: -0.0000

Data Index: 798354 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4306. Min Act: -0.0000

Data Index: 823899 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1173456 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4331. Min Act: -0.0000

Data Index: 249090 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4118. Min Act: -0.0000

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4036. Min Act: -0.0000

Data Index: 605268 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1056587 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4297. Min Act: -0.0000

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4155. Min Act: -0.0000

Data Index: 901532 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1291049 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.3958. Min Act: -0.0000

Data Index: 428917 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.5786. Min Range: -0.5786

Max Act: 0.4165. Min Act: -0.0000

Data Index: 653938 (C4 (Web Text))

Max Activating Token Index: 174