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

Dataset: The Pile

Neuron 2112 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0373. Min Range: -7.0373

Max Act: 7.0373. Min Act: -0.0000

Data Index: 1782590 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.6832. Min Act: -0.0000

Data Index: 1700280 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.8298. Min Act: -0.0000

Data Index: 235328 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.7428. Min Act: -0.0000

Data Index: 1162631 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 7.0373. Min Range: -7.0373

Max Act: 6.0370. Min Act: -0.0000

Data Index: 1193388 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.5496. Min Act: -0.0000

Data Index: 1472099 (The Pile)

Max Activating Token Index: 785

Text #6

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.3094. Min Act: -0.0000

Data Index: 1742870 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.2079. Min Act: -0.0000

Data Index: 1247644 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.1567. Min Act: -0.0000

Data Index: 1432866 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.2778. Min Act: -0.0000

Data Index: 1220258 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.1892. Min Act: -0.0000

Data Index: 1197623 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 7.0373. Min Range: -7.0373

Max Act: 4.8192. Min Act: -0.0000

Data Index: 529587 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.3198. Min Act: -0.0000

Data Index: 111812 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 7.0373. Min Range: -7.0373

Max Act: 4.9183. Min Act: -0.0000

Data Index: 897575 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 7.0373. Min Range: -7.0373

Max Act: 4.4974. Min Act: -0.0000

Data Index: 1299646 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.0713. Min Act: -0.0000

Data Index: 865372 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 7.0373. Min Range: -7.0373

Max Act: 5.3880. Min Act: -0.0000

Data Index: 425107 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 7.0373. Min Range: -7.0373

Max Act: 4.9951. Min Act: -0.0000

Data Index: 1993068 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 7.0373. Min Range: -7.0373

Max Act: 4.3741. Min Act: -0.0000

Data Index: 344430 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 7.0373. Min Range: -7.0373

Max Act: 4.9296. Min Act: -0.0000

Data Index: 145061 (The Pile)

Max Activating Token Index: 55