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

Dataset: The Pile

Neuron 4160 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: 0.4608. Min Range: -0.4608

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1705938 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3240. Min Act: -0.0000

Data Index: 480525 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1164610 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2915. Min Act: -0.0000

Data Index: 933284 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1962298 (The Pile)

Max Activating Token Index: 329

Text #5

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1336011 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1753566 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1436632 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1910386 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1514869 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2615. Min Act: -0.0000

Data Index: 594395 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2580. Min Act: -0.0000

Data Index: 542233 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1587424 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2292. Min Act: -0.0000

Data Index: 992157 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2352. Min Act: -0.0000

Data Index: 75807 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1129682 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1192177 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2198. Min Act: -0.0000

Data Index: 922830 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1790792 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1482897 (The Pile)

Max Activating Token Index: 175