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

Dataset: The Pile

Neuron 3302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1573004 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1251853 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1812583 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1156585 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1065523 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5953. Min Act: -0.0000

Data Index: 27099 (The Pile)

Max Activating Token Index: 820

Text #6

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1355801 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1148455 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5367. Min Act: -0.0000

Data Index: 886027 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1832547 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5515. Min Act: -0.0000

Data Index: 677834 (The Pile)

Max Activating Token Index: 436

Text #11

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5189. Min Act: -0.0000

Data Index: 665480 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5620. Min Act: -0.0000

Data Index: 838656 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1295050 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4261. Min Act: -0.0000

Data Index: 263222 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4957. Min Act: -0.0000

Data Index: 232856 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5032. Min Act: -0.0000

Data Index: 308077 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1826358 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5702. Min Act: -0.0000

Data Index: 148122 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5153. Min Act: -0.0000

Data Index: 136355 (The Pile)

Max Activating Token Index: 434