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

Dataset: The Pile

Neuron 3138 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: 0.5452. Min Range: -0.5452

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1794652 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1767181 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4650. Min Act: -0.0000

Data Index: 360024 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1806365 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1436253 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1769763 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4001. Min Act: -0.0000

Data Index: 157409 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1549063 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3822. Min Act: -0.0000

Data Index: 847643 (The Pile)

Max Activating Token Index: 644

Text #9

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1163971 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1773172 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3962. Min Act: -0.0000

Data Index: 587012 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3711. Min Act: -0.0000

Data Index: 199876 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1449861 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1465358 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3836. Min Act: -0.0000

Data Index: 114557 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1225872 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1402779 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1658226 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1785358 (The Pile)

Max Activating Token Index: 507