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

Dataset: The Pile

Neuron 1531 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: 0.4317. Min Range: -0.4317

Max Act: 0.4317. Min Act: -0.0000

Data Index: 499342 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1387479 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1111206 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1167705 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3313. Min Act: -0.0000

Data Index: 628591 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3068. Min Act: -0.0000

Data Index: 622701 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1712348 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1432182 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1156595 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3057. Min Act: -0.0000

Data Index: 577735 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3173. Min Act: -0.0000

Data Index: 795369 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2842. Min Act: -0.0000

Data Index: 362723 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1075981 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1026225 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2928. Min Act: -0.0000

Data Index: 937255 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2965. Min Act: -0.0000

Data Index: 149825 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2780. Min Act: -0.0000

Data Index: 856124 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.3046. Min Act: -0.0000

Data Index: 632049 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1233373 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 0.4317. Min Range: -0.4317

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1359583 (The Pile)

Max Activating Token Index: 311