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

Dataset: The Pile

Neuron 600 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: 1.2842. Min Range: -1.2842

Max Act: 1.2842. Min Act: -0.0000

Data Index: 1942857 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1235583 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1819954 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1719. Min Act: -0.0000

Data Index: 304343 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.2239. Min Act: -0.0000

Data Index: 186458 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1094177 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1554. Min Act: -0.0000

Data Index: 616526 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.2291. Min Act: -0.0000

Data Index: 1561177 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1427. Min Act: -0.0000

Data Index: 118514 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1074. Min Act: -0.0000

Data Index: 952676 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1361. Min Act: -0.0000

Data Index: 1729143 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1741. Min Act: -0.0000

Data Index: 213645 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1944955 (The Pile)

Max Activating Token Index: 490

Text #13

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1967324 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1019334 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1011. Min Act: -0.0000

Data Index: 28657 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1615880 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1593025 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.1235. Min Act: -0.0000

Data Index: 434148 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 1.2842. Min Range: -1.2842

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1816211 (The Pile)

Max Activating Token Index: 660