Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 745 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1299534 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1480. Min Act: -0.0000

Data Index: 179733 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1372. Min Act: -0.0000

Data Index: 350489 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1931051 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1384. Min Act: -0.0000

Data Index: 133689 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1303. Min Act: -0.0000

Data Index: 114726 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1345690 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1794924 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1302923 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1290757 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1201. Min Act: -0.0001

Data Index: 453787 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1137. Min Act: -0.0000

Data Index: 194398 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1986494 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1006. Min Act: 0.0000

Data Index: 1703487 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.0951. Min Act: -0.0000

Data Index: 443751 (The Pile)

Max Activating Token Index: 624

Text #15

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1565633 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1742967 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1497158 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1175. Min Act: -0.0000

Data Index: 465139 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1049. Min Act: -0.0000

Data Index: 617991 (The Pile)

Max Activating Token Index: 372