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

Dataset: The Pile

Neuron 4436 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: 6.1736. Min Range: -6.1736

Max Act: 6.1736. Min Act: -0.0000

Data Index: 1576083 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.8304. Min Act: -0.0000

Data Index: 542990 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.8175. Min Act: -0.0000

Data Index: 1157330 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.6053. Min Act: -0.0000

Data Index: 1186670 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.5247. Min Act: -0.0000

Data Index: 820507 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.4900. Min Act: -0.0000

Data Index: 1679030 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.4777. Min Act: -0.0000

Data Index: 1275941 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.3868. Min Act: -0.0000

Data Index: 580403 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.3557. Min Act: -0.0000

Data Index: 1883008 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.2784. Min Act: -0.0000

Data Index: 1139315 (The Pile)

Max Activating Token Index: 480

Text #10

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.2660. Min Act: -0.0000

Data Index: 560489 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.2544. Min Act: -0.0000

Data Index: 660800 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.0507. Min Act: -0.0000

Data Index: 238175 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.0007. Min Act: -0.0000

Data Index: 1996624 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.1335. Min Act: -0.0000

Data Index: 332233 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.1136. Min Act: -0.0000

Data Index: 150071 (The Pile)

Max Activating Token Index: 351

Text #16

Max Range: 6.1736. Min Range: -6.1736

Max Act: 4.9202. Min Act: -0.0000

Data Index: 1274950 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.2704. Min Act: -0.0000

Data Index: 1879075 (The Pile)

Max Activating Token Index: 144

Text #18

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.2724. Min Act: -0.0000

Data Index: 794526 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 6.1736. Min Range: -6.1736

Max Act: 5.2552. Min Act: -0.0000

Data Index: 495323 (The Pile)

Max Activating Token Index: 401