Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 643 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1262204 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1990644 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4761. Min Act: -0.0000

Data Index: 565324 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1855357 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4621. Min Act: -0.0000

Data Index: 954532 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1278280 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1091119 (The Pile)

Max Activating Token Index: 917

Text #7

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4797. Min Act: -0.0000

Data Index: 830744 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4495. Min Act: -0.0000

Data Index: 22017 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1294510 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1024574 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4348. Min Act: -0.0000

Data Index: 525754 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1999327 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4469. Min Act: -0.0000

Data Index: 639901 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4460. Min Act: -0.0001

Data Index: 837296 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1446582 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1032531 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1663344 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1825531 (The Pile)

Max Activating Token Index: 946

Text #19

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4306. Min Act: -0.0000

Data Index: 119503 (The Pile)

Max Activating Token Index: 582