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

Dataset: The Pile

Neuron 392 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: 0.9489. Min Range: -0.9489

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1223888 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1780455 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1222306 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1791981 (The Pile)

Max Activating Token Index: 657

Text #4

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6951. Min Act: -0.0000

Data Index: 78594 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.8357. Min Act: -0.0000

Data Index: 53776 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1654033 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1831312 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1377006 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6751. Min Act: -0.0000

Data Index: 109898 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1392233 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.7031. Min Act: -0.0000

Data Index: 262356 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6561. Min Act: -0.0000

Data Index: 931137 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6548. Min Act: -0.0000

Data Index: 347208 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1205122 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1990524 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1425693 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.4719. Min Act: -0.0000

Data Index: 59376 (The Pile)

Max Activating Token Index: 934

Text #18

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1142660 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.9489. Min Range: -0.9489

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1452341 (The Pile)

Max Activating Token Index: 426