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

Dataset: The Pile

Neuron 4062 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1714358 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4141. Min Act: -0.0000

Data Index: 35377 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1774282 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1277268 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1086789 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1854151 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4162. Min Act: -0.0000

Data Index: 812611 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3971. Min Act: -0.0000

Data Index: 886525 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1300580 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3663. Min Act: -0.0000

Data Index: 296001 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3840. Min Act: -0.0000

Data Index: 21890 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3680. Min Act: -0.0000

Data Index: 172328 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3294. Min Act: -0.0000

Data Index: 225269 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3858. Min Act: -0.0000

Data Index: 914149 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4181. Min Act: -0.0000

Data Index: 314044 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3433. Min Act: -0.0000

Data Index: 490149 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3777. Min Act: -0.0000

Data Index: 542721 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3748. Min Act: -0.0000

Data Index: 212405 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3616. Min Act: -0.0000

Data Index: 349428 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1668032 (The Pile)

Max Activating Token Index: 388