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

Dataset: The Pile

Neuron 3653 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1098443 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.7280. Min Act: -0.0000

Data Index: 306876 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6484. Min Act: 0.0001

Data Index: 76949 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1638046 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.6080. Min Act: -0.0000

Data Index: 81691 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1483302 (The Pile)

Max Activating Token Index: 309

Text #6

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1980228 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5334. Min Act: 0.0000

Data Index: 1805989 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5268. Min Act: -0.0000

Data Index: 5867 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5174. Min Act: -0.0000

Data Index: 329152 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5093. Min Act: -0.0000

Data Index: 242369 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1617697 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1733582 (The Pile)

Max Activating Token Index: 550

Text #13

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5194. Min Act: -0.0000

Data Index: 229069 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5171. Min Act: -0.0000

Data Index: 866974 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.5145. Min Act: 0.0000

Data Index: 435960 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.4662. Min Act: -0.0000

Data Index: 337079 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.4683. Min Act: 0.0000

Data Index: 1459967 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1119044 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 0.8530. Min Range: -0.8530

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1951699 (The Pile)

Max Activating Token Index: 450