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

Dataset: The Pile

Neuron 2933 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: 0.9735. Min Range: -0.9735

Max Act: 0.9735. Min Act: -0.0000

Data Index: 915815 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1413297 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1197549 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8470. Min Act: -0.0000

Data Index: 328556 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8663. Min Act: -0.0000

Data Index: 446379 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8118. Min Act: -0.0000

Data Index: 394326 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8632. Min Act: -0.0000

Data Index: 368224 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1314988 (The Pile)

Max Activating Token Index: 846

Text #8

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1439502 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8927. Min Act: -0.0000

Data Index: 278117 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8281. Min Act: -0.0000

Data Index: 855714 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1434296 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8510. Min Act: -0.0000

Data Index: 856856 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1364273 (The Pile)

Max Activating Token Index: 899

Text #14

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8693. Min Act: -0.0000

Data Index: 425625 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1744157 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1692419 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8071. Min Act: -0.0000

Data Index: 534037 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8283. Min Act: -0.0000

Data Index: 189006 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 0.9735. Min Range: -0.9735

Max Act: 0.8268. Min Act: -0.0000

Data Index: 571108 (The Pile)

Max Activating Token Index: 456