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

Dataset: The Pile

Neuron 4999 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: 1.9272. Min Range: -1.9272

Max Act: 1.9272. Min Act: -0.0000

Data Index: 545948 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.7510. Min Act: -0.0000

Data Index: 1277261 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.7388. Min Act: -0.0000

Data Index: 377921 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.7702. Min Act: -0.0000

Data Index: 1718266 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5665. Min Act: -0.0000

Data Index: 1497591 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5369. Min Act: -0.0000

Data Index: 1060465 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.6149. Min Act: -0.0000

Data Index: 382629 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5970. Min Act: -0.0000

Data Index: 592737 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4957. Min Act: -0.0000

Data Index: 1653594 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1527960 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5694. Min Act: -0.0000

Data Index: 853433 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5545. Min Act: -0.0000

Data Index: 861257 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1524599 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4916. Min Act: -0.0000

Data Index: 1552632 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4325. Min Act: -0.0000

Data Index: 475152 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4047. Min Act: -0.0000

Data Index: 327321 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1671642 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.3814. Min Act: -0.0000

Data Index: 243137 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.4312. Min Act: -0.0000

Data Index: 1105700 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 1.9272. Min Range: -1.9272

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1955292 (The Pile)

Max Activating Token Index: 623