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

Dataset: The Pile

Neuron 801 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: 1.8664. Min Range: -1.8664

Max Act: 1.8664. Min Act: -0.0000

Data Index: 153816 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1129301 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.6439. Min Act: -0.0000

Data Index: 1339170 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.5014. Min Act: -0.0000

Data Index: 274698 (The Pile)

Max Activating Token Index: 8

Text #4

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.5008. Min Act: -0.0000

Data Index: 927940 (The Pile)

Max Activating Token Index: 649

Text #5

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1826707 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.4113. Min Act: -0.0000

Data Index: 111073 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.3142. Min Act: -0.0000

Data Index: 954610 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1258339 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.3418. Min Act: -0.0000

Data Index: 1664492 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1769176 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1782261 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1786689 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1454643 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1251639 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.3636. Min Act: -0.0000

Data Index: 1144158 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.2794. Min Act: -0.0000

Data Index: 766316 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1372060 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1001850 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 1.8664. Min Range: -1.8664

Max Act: 1.2299. Min Act: -0.0000

Data Index: 869765 (The Pile)

Max Activating Token Index: 672