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

Dataset: The Pile

Neuron 2485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1341414 (The Pile)

Max Activating Token Index: 181

Text #1

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3817. Min Act: -0.0000

Data Index: 763260 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1437604 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3513. Min Act: -0.0000

Data Index: 636190 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3501. Min Act: -0.0000

Data Index: 102263 (The Pile)

Max Activating Token Index: 315

Text #5

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3275. Min Act: -0.0000

Data Index: 346951 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1349236 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3475. Min Act: -0.0000

Data Index: 613656 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3342. Min Act: -0.0000

Data Index: 664458 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1315536 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3296. Min Act: -0.0000

Data Index: 129344 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3109. Min Act: -0.0000

Data Index: 114373 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3058. Min Act: -0.0000

Data Index: 641605 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3175. Min Act: -0.0000

Data Index: 191915 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1680997 (The Pile)

Max Activating Token Index: 964

Text #15

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1446172 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3111. Min Act: -0.0000

Data Index: 495168 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1965959 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1944396 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.4071. Min Range: -0.4071

Max Act: 0.3265. Min Act: -0.0000

Data Index: 834956 (The Pile)

Max Activating Token Index: 101