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

Dataset: The Pile

Neuron 1040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1054249 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.8555. Min Act: -0.0000

Data Index: 496288 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7999. Min Act: -0.0000

Data Index: 808047 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7792. Min Act: -0.0000

Data Index: 597249 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1673563 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7780. Min Act: -0.0000

Data Index: 965834 (The Pile)

Max Activating Token Index: 220

Text #6

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1174494 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1185578 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1397371 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1231996 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6714. Min Act: -0.0000

Data Index: 610944 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1111182 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7348. Min Act: -0.0000

Data Index: 911031 (The Pile)

Max Activating Token Index: 202

Text #13

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6488. Min Act: -0.0000

Data Index: 645823 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1651459 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6796. Min Act: -0.0000

Data Index: 587758 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6666. Min Act: -0.0000

Data Index: 252037 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7109. Min Act: -0.0000

Data Index: 390650 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1147126 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1003403 (The Pile)

Max Activating Token Index: 165