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

Dataset: The Pile

Neuron 1111 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5358. Min Act: -0.0000

Data Index: 841048 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4948. Min Act: -0.0000

Data Index: 967095 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4503. Min Act: -0.0000

Data Index: 207683 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4580. Min Act: -0.0000

Data Index: 2986 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4183. Min Act: -0.0000

Data Index: 737871 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4391. Min Act: -0.0000

Data Index: 60359 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4403. Min Act: -0.0000

Data Index: 192484 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4396. Min Act: -0.0000

Data Index: 574972 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1663069 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1285800 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4170. Min Act: -0.0000

Data Index: 181118 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4326. Min Act: -0.0000

Data Index: 115465 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4190. Min Act: -0.0000

Data Index: 190049 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1647536 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3993. Min Act: -0.0000

Data Index: 329685 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4132. Min Act: -0.0000

Data Index: 824872 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4290. Min Act: -0.0000

Data Index: 109277 (The Pile)

Max Activating Token Index: 335

Text #17

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1220530 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4128. Min Act: -0.0000

Data Index: 420147 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4276. Min Act: -0.0000

Data Index: 331033 (The Pile)

Max Activating Token Index: 458