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

Dataset: The Pile

Neuron 1098 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: 0.5131. Min Range: -0.5131

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1411477 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3428. Min Act: -0.0000

Data Index: 513359 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3264. Min Act: -0.0000

Data Index: 834857 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1751818 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2878. Min Act: -0.0000

Data Index: 589006 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1219080 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.3117. Min Act: -0.0000

Data Index: 39188 (The Pile)

Max Activating Token Index: 236

Text #7

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2824. Min Act: -0.0000

Data Index: 11210 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1060451 (The Pile)

Max Activating Token Index: 450

Text #9

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2849. Min Act: -0.0000

Data Index: 83778 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1948246 (The Pile)

Max Activating Token Index: 337

Text #11

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1881215 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2501. Min Act: -0.0000

Data Index: 640024 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2389. Min Act: -0.0000

Data Index: 235914 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1783227 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1630330 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1946072 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2305. Min Act: -0.0000

Data Index: 640951 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1724861 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 0.5131. Min Range: -0.5131

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1590927 (The Pile)

Max Activating Token Index: 951