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

Dataset: The Pile

Neuron 1778 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1911457 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.6063. Min Act: 0.0000

Data Index: 1119144 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5771. Min Act: 0.0000

Data Index: 1700146 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5968. Min Act: -0.0000

Data Index: 37916 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.6119. Min Act: -0.0000

Data Index: 377127 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5479. Min Act: -0.0000

Data Index: 139896 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1058899 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5641. Min Act: -0.0000

Data Index: 114948 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1325147 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4961. Min Act: 0.0000

Data Index: 1679841 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1911041 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4336. Min Act: -0.0000

Data Index: 396204 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4787. Min Act: 0.0000

Data Index: 1377889 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1082809 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.5286. Min Act: 0.0000

Data Index: 1746149 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4462. Min Act: -0.0000

Data Index: 748740 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1879935 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1757298 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1329226 (The Pile)

Max Activating Token Index: 973

Text #19

Max Range: 0.6423. Min Range: -0.6423

Max Act: 0.4634. Min Act: -0.0000

Data Index: 707120 (The Pile)

Max Activating Token Index: 611