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

Dataset: The Pile

Neuron 3275 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: 1.1257. Min Range: -1.1257

Max Act: 1.0638. Min Act: -0.0000

Data Index: 633687 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 1.1257. Min Range: -1.1257

Max Act: 1.1257. Min Act: -0.0000

Data Index: 186430 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.1257. Min Range: -1.1257

Max Act: 1.0850. Min Act: -0.0000

Data Index: 399141 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 1.1257. Min Range: -1.1257

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1434895 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 1.1257. Min Range: -1.1257

Max Act: 1.0595. Min Act: -0.0000

Data Index: 497178 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1237162 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1261992 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8932. Min Act: -0.0000

Data Index: 307806 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1191891 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1416420 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1267927 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9319. Min Act: -0.0000

Data Index: 707425 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9474. Min Act: -0.0000

Data Index: 369600 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1623452 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1426427 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9156. Min Act: -0.0000

Data Index: 792907 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8592. Min Act: -0.0000

Data Index: 213100 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1988426 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1091582 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 1.1257. Min Range: -1.1257

Max Act: 0.8781. Min Act: -0.0000

Data Index: 816911 (The Pile)

Max Activating Token Index: 683