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

Dataset: The Pile

Neuron 99 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3721. Min Range: -7.3721

Max Act: 7.3721. Min Act: -0.0000

Data Index: 1259193 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.9525. Min Act: -0.0000

Data Index: 1803857 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 7.3721. Min Range: -7.3721

Max Act: 5.0201. Min Act: -0.0000

Data Index: 1895359 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.2630. Min Act: -0.0000

Data Index: 1482894 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.7555. Min Act: 0.0001

Data Index: 718228 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.6750. Min Act: -0.0000

Data Index: 308925 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.5571. Min Act: 0.0000

Data Index: 1317124 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.6532. Min Act: -0.0000

Data Index: 1694321 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.1191. Min Act: -0.0000

Data Index: 1369112 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.5502. Min Act: -0.0000

Data Index: 1561850 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 7.3721. Min Range: -7.3721

Max Act: 4.0577. Min Act: -0.0000

Data Index: 185250 (The Pile)

Max Activating Token Index: 286

Text #11

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.9716. Min Act: -0.0000

Data Index: 271110 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.7883. Min Act: 0.0000

Data Index: 1138671 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.9181. Min Act: -0.0000

Data Index: 214419 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.9104. Min Act: -0.0000

Data Index: 1175280 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.6090. Min Act: -0.0000

Data Index: 1351652 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.7640. Min Act: -0.0000

Data Index: 1451162 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.8652. Min Act: 0.0000

Data Index: 1082819 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.7361. Min Act: -0.0000

Data Index: 500808 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 7.3721. Min Range: -7.3721

Max Act: 3.5356. Min Act: -0.0000

Data Index: 596989 (The Pile)

Max Activating Token Index: 577