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

Dataset: The Pile

Neuron 2402 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: 3.8216. Min Range: -3.8216

Max Act: 3.8216. Min Act: -0.0000

Data Index: 398154 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.7102. Min Act: -0.0000

Data Index: 159939 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.5182. Min Act: -0.0000

Data Index: 1599268 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.4748. Min Act: -0.0000

Data Index: 1081924 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.4637. Min Act: -0.0000

Data Index: 974506 (The Pile)

Max Activating Token Index: 638

Text #5

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.4291. Min Act: -0.0000

Data Index: 204371 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.5723. Min Act: -0.0000

Data Index: 1368716 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.3358. Min Act: -0.0000

Data Index: 1191987 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.4654. Min Act: -0.0000

Data Index: 236500 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.4420. Min Act: -0.0000

Data Index: 817464 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.2738. Min Act: -0.0000

Data Index: 1071408 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.2502. Min Act: -0.0000

Data Index: 967562 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.0700. Min Act: -0.0000

Data Index: 701228 (The Pile)

Max Activating Token Index: 206

Text #13

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.3220. Min Act: -0.0000

Data Index: 1106938 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1656. Min Act: -0.0000

Data Index: 840761 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.0201. Min Act: -0.0000

Data Index: 1915534 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1420. Min Act: -0.0000

Data Index: 1402513 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1496. Min Act: -0.0000

Data Index: 132746 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1258. Min Act: -0.0000

Data Index: 583911 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 3.8216. Min Range: -3.8216

Max Act: 3.1248. Min Act: -0.0000

Data Index: 1729176 (The Pile)

Max Activating Token Index: 227