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

Dataset: The Pile

Neuron 209 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.6434. Min Act: -0.0000

Data Index: 713718 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.6086. Min Act: -0.0000

Data Index: 405228 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.6184. Min Act: -0.0000

Data Index: 459954 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5947. Min Act: -0.0000

Data Index: 727293 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5237. Min Act: -0.0000

Data Index: 320560 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1031978 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5231. Min Act: -0.0000

Data Index: 408029 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1311530 (The Pile)

Max Activating Token Index: 453

Text #8

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1120595 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1762407 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4949. Min Act: -0.0000

Data Index: 127845 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4888. Min Act: -0.0000

Data Index: 856061 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4908. Min Act: -0.0000

Data Index: 39617 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4801. Min Act: -0.0000

Data Index: 321895 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1330490 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1441554 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1833147 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1608905 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4681. Min Act: -0.0000

Data Index: 183169 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1262284 (The Pile)

Max Activating Token Index: 374