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

Dataset: The Pile

Neuron 1786 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6019. Min Act: -0.0000

Data Index: 1790793 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.7450. Min Act: -0.0000

Data Index: 1434721 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.5069. Min Act: 0.0000

Data Index: 1114294 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4943. Min Act: -0.0000

Data Index: 67031 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4158. Min Act: -0.0000

Data Index: 172679 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4095. Min Act: -0.0000

Data Index: 232344 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4649. Min Act: -0.0000

Data Index: 1820728 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1627828 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.2507. Min Act: -0.0000

Data Index: 134646 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1026668 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4019. Min Act: -0.0000

Data Index: 686443 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1477424 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1683982 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1745. Min Act: -0.0000

Data Index: 1556811 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1014. Min Act: -0.0000

Data Index: 18300 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1448. Min Act: -0.0000

Data Index: 560130 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1362. Min Act: -0.0000

Data Index: 738142 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1293848 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0433. Min Act: -0.0000

Data Index: 695650 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1531. Min Act: -0.0000

Data Index: 806713 (The Pile)

Max Activating Token Index: 121