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

Dataset: The Pile

Neuron 3479 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: 3.7929. Min Range: -3.7929

Max Act: 3.7929. Min Act: -0.0000

Data Index: 1576018 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.5815. Min Act: -0.0000

Data Index: 516638 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.6031. Min Act: -0.0000

Data Index: 270214 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.2342. Min Act: -0.0000

Data Index: 1298064 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.9853. Min Act: -0.0000

Data Index: 1239770 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.8881. Min Act: -0.0000

Data Index: 1905267 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 3.7929. Min Range: -3.7929

Max Act: 3.0190. Min Act: -0.0000

Data Index: 1288207 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.7014. Min Act: -0.0000

Data Index: 474372 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.9121. Min Act: -0.0000

Data Index: 588354 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.7557. Min Act: -0.0000

Data Index: 1736855 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.8550. Min Act: -0.0000

Data Index: 1829238 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.7880. Min Act: -0.0000

Data Index: 843358 (The Pile)

Max Activating Token Index: 101

Text #12

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.6769. Min Act: -0.0000

Data Index: 460059 (The Pile)

Max Activating Token Index: 769

Text #13

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.8168. Min Act: -0.0000

Data Index: 1642770 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.5519. Min Act: -0.0000

Data Index: 1178806 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.3304. Min Act: -0.0000

Data Index: 385240 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.4425. Min Act: -0.0000

Data Index: 1999091 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.6962. Min Act: -0.0000

Data Index: 1202620 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.6150. Min Act: -0.0000

Data Index: 360809 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 3.7929. Min Range: -3.7929

Max Act: 2.5968. Min Act: -0.0000

Data Index: 1632473 (The Pile)

Max Activating Token Index: 789