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

Dataset: The Pile

Neuron 1414 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1739460 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1748159 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1354451 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3425. Min Act: -0.0000

Data Index: 911025 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1591780 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2805. Min Act: -0.0000

Data Index: 541548 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1312446 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2484. Min Act: -0.0000

Data Index: 348691 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1254248 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2635. Min Act: -0.0000

Data Index: 513943 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1447284 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2503. Min Act: -0.0000

Data Index: 314718 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1129022 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1833969 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1303040 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1143509 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2482. Min Act: -0.0000

Data Index: 217681 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2339. Min Act: -0.0000

Data Index: 238145 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1565879 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1253598 (The Pile)

Max Activating Token Index: 665