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

Dataset: The Pile

Neuron 2620 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: 0.6060. Min Range: -0.6060

Max Act: 0.6060. Min Act: -0.0000

Data Index: 102453 (The Pile)

Max Activating Token Index: 261

Text #1

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5714. Min Act: -0.0000

Data Index: 768075 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5664. Min Act: 0.0000

Data Index: 1233589 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5162. Min Act: 0.0000

Data Index: 548104 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5035. Min Act: -0.0000

Data Index: 163610 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1580078 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1386944 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5346. Min Act: -0.0000

Data Index: 900341 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1154601 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5241. Min Act: -0.0000

Data Index: 256347 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1292947 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4878. Min Act: -0.0000

Data Index: 820599 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1121074 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4834. Min Act: -0.0000

Data Index: 550700 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4797. Min Act: 0.0000

Data Index: 90341 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4544. Min Act: -0.0000

Data Index: 920831 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1838054 (The Pile)

Max Activating Token Index: 943

Text #17

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4330. Min Act: -0.0000

Data Index: 686438 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1685137 (The Pile)

Max Activating Token Index: 579

Text #19

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4304. Min Act: -0.0000

Data Index: 28468 (The Pile)

Max Activating Token Index: 148