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

Dataset: The Pile

Neuron 1653 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.4040. Min Act: -0.0000

Data Index: 392634 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1407. Min Act: -0.0000

Data Index: 563125 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.1517. Min Act: -0.0000

Data Index: 658502 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1882154 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 1.4040. Min Range: -1.4040

Max Act: 1.0077. Min Act: -0.0000

Data Index: 617461 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1303470 (The Pile)

Max Activating Token Index: 869

Text #6

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1961156 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1587034 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.8689. Min Act: -0.0000

Data Index: 319800 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1112003 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1872643 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.7681. Min Act: -0.0000

Data Index: 917082 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1437929 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1361492 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1643402 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1242920 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.8115. Min Act: -0.0001

Data Index: 1541290 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.7330. Min Act: -0.0000

Data Index: 725520 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.8808. Min Act: -0.0000

Data Index: 469364 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 1.4040. Min Range: -1.4040

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1237399 (The Pile)

Max Activating Token Index: 945