Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2009 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.2166. Min Act: -0.0000

Data Index: 1297821 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1251630 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1349770 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1416344 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1830683 (The Pile)

Max Activating Token Index: 697

Text #5

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1823075 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.1455. Min Act: -0.0000

Data Index: 39927 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1377252 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1835482 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0963. Min Act: -0.0000

Data Index: 349007 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1060212 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0553. Min Act: -0.0000

Data Index: 490435 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1159521 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0720. Min Act: -0.0000

Data Index: 946429 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1029301 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1745652 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1779733 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9923. Min Act: -0.0000

Data Index: 963162 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9856. Min Act: -0.0000

Data Index: 85699 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9613. Min Act: -0.0000

Data Index: 717601 (The Pile)

Max Activating Token Index: 355