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

Dataset: The Pile

Neuron 628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1442844 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.9290. Min Act: -0.0000

Data Index: 838181 (The Pile)

Max Activating Token Index: 84

Text #2

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8771. Min Act: -0.0000

Data Index: 355209 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1484531 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.9353. Min Act: -0.0000

Data Index: 663983 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1040699 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8783. Min Act: -0.0000

Data Index: 370327 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.7638. Min Act: -0.0000

Data Index: 638244 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1188335 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1471486 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.7979. Min Act: -0.0000

Data Index: 679985 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8436. Min Act: -0.0000

Data Index: 41265 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1271429 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.7532. Min Act: -0.0000

Data Index: 954017 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.8037. Min Act: -0.0000

Data Index: 555317 (The Pile)

Max Activating Token Index: 195

Text #15

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1473996 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1165139 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1664099 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.7396. Min Act: -0.0000

Data Index: 240155 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 0.9353. Min Range: -0.9353

Max Act: 0.7811. Min Act: -0.0000

Data Index: 738404 (The Pile)

Max Activating Token Index: 167