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

Dataset: The Pile

Neuron 3828 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3470. Min Range: -5.3470

Max Act: 5.1390. Min Act: -0.0000

Data Index: 549671 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 5.3470. Min Range: -5.3470

Max Act: 5.3470. Min Act: -0.0000

Data Index: 1869308 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 5.3470. Min Range: -5.3470

Max Act: 5.2637. Min Act: -0.0000

Data Index: 1508073 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 5.3470. Min Range: -5.3470

Max Act: 5.0084. Min Act: -0.0000

Data Index: 1930213 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.9454. Min Act: -0.0000

Data Index: 24318 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 5.3470. Min Range: -5.3470

Max Act: 5.0817. Min Act: -0.0000

Data Index: 349109 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 5.3470. Min Range: -5.3470

Max Act: 5.0166. Min Act: -0.0000

Data Index: 486637 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.7099. Min Act: -0.0000

Data Index: 1321004 (The Pile)

Max Activating Token Index: 709

Text #8

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.5368. Min Act: -0.0000

Data Index: 1806190 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.4135. Min Act: -0.0000

Data Index: 1141156 (The Pile)

Max Activating Token Index: 61

Text #10

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.4080. Min Act: -0.0000

Data Index: 1290581 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.3566. Min Act: -0.0000

Data Index: 253694 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.5855. Min Act: -0.0000

Data Index: 1555155 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.1807. Min Act: -0.0000

Data Index: 212227 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.5008. Min Act: -0.0000

Data Index: 1615978 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.4916. Min Act: -0.0000

Data Index: 4459 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.4606. Min Act: -0.0000

Data Index: 1549802 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.4179. Min Act: -0.0000

Data Index: 34871 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.2534. Min Act: -0.0000

Data Index: 1336251 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 5.3470. Min Range: -5.3470

Max Act: 4.1923. Min Act: -0.0000

Data Index: 1656577 (The Pile)

Max Activating Token Index: 645