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

Dataset: The Pile

Neuron 1815 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8526. Min Act: -0.0000

Data Index: 615231 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1951631 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8471. Min Act: -0.0000

Data Index: 809720 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7960. Min Act: -0.0000

Data Index: 498031 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7444. Min Act: -0.0000

Data Index: 614504 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1822262 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1952275 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1735301 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.8709. Min Act: -0.0000

Data Index: 320497 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1116928 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1801456 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1362145 (The Pile)

Max Activating Token Index: 99

Text #12

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7328. Min Act: -0.0000

Data Index: 41442 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7102. Min Act: -0.0000

Data Index: 23243 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7423. Min Act: -0.0000

Data Index: 206507 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1926415 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1085827 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1464304 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6582. Min Act: -0.0000

Data Index: 671847 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.8798. Min Range: -0.8798

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1511851 (The Pile)

Max Activating Token Index: 199