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

Dataset: The Pile

Neuron 762 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: 1.7453. Min Range: -1.7453

Max Act: 1.6408. Min Act: -0.0000

Data Index: 1965064 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.6543. Min Act: -0.0000

Data Index: 466903 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1831492 (The Pile)

Max Activating Token Index: 181

Text #3

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.5910. Min Act: -0.0000

Data Index: 738001 (The Pile)

Max Activating Token Index: 884

Text #4

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.7453. Min Act: -0.0000

Data Index: 1993503 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1853863 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1242649 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.5283. Min Act: -0.0000

Data Index: 1577430 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3327. Min Act: -0.0000

Data Index: 858319 (The Pile)

Max Activating Token Index: 452

Text #9

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2885. Min Act: -0.0000

Data Index: 470420 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1195190 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3402. Min Act: -0.0000

Data Index: 434300 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3031. Min Act: -0.0001

Data Index: 1822126 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2956. Min Act: -0.0000

Data Index: 81153 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3709. Min Act: -0.0000

Data Index: 1826704 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1425729 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2565. Min Act: -0.0000

Data Index: 1231884 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3322. Min Act: -0.0000

Data Index: 1747011 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.3506. Min Act: -0.0000

Data Index: 347578 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 1.7453. Min Range: -1.7453

Max Act: 1.2511. Min Act: -0.0000

Data Index: 639105 (The Pile)

Max Activating Token Index: 265