Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4685 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1499819 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.6146. Min Act: -0.0000

Data Index: 770179 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1515682 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.6356. Min Act: -0.0000

Data Index: 984630 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5991. Min Act: -0.0000

Data Index: 447058 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1461993 (The Pile)

Max Activating Token Index: 570

Text #6

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.6491. Min Act: -0.0000

Data Index: 144300 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1283808 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1463794 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1966341 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.6074. Min Act: -0.0000

Data Index: 247262 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5159. Min Act: -0.0000

Data Index: 900503 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4598. Min Act: -0.0000

Data Index: 217776 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5194. Min Act: -0.0000

Data Index: 486252 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4745. Min Act: -0.0000

Data Index: 504198 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1081519 (The Pile)

Max Activating Token Index: 325

Text #16

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1220953 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4719. Min Act: -0.0000

Data Index: 714232 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1094823 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4547. Min Act: -0.0000

Data Index: 433995 (The Pile)

Max Activating Token Index: 310