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

Dataset: The Pile

Neuron 7 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: 0.4349. Min Range: -0.4349

Max Act: 0.4349. Min Act: -0.0000

Data Index: 487428 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1770155 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1806926 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1061398 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3281. Min Act: -0.0000

Data Index: 746051 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1281807 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1220289 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1383431 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2917. Min Act: -0.0000

Data Index: 795338 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3053. Min Act: -0.0000

Data Index: 678763 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1887078 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2936. Min Act: -0.0000

Data Index: 451670 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2869. Min Act: -0.0000

Data Index: 217051 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1954980 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2564. Min Act: -0.0000

Data Index: 700147 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1868740 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1559596 (The Pile)

Max Activating Token Index: 726

Text #17

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1625125 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2707. Min Act: -0.0000

Data Index: 178074 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1190004 (The Pile)

Max Activating Token Index: 604