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

Dataset: The Pile

Neuron 3221 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.6261. Min Act: -0.0000

Data Index: 465961 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.5437. Min Act: -0.0000

Data Index: 809598 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1133045 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4794. Min Act: -0.0000

Data Index: 761951 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1179873 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4696. Min Act: -0.0000

Data Index: 994851 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1236177 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1312503 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4508. Min Act: -0.0000

Data Index: 748037 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4791. Min Act: -0.0000

Data Index: 731938 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4629. Min Act: -0.0000

Data Index: 609541 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1627944 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4401. Min Act: -0.0000

Data Index: 543137 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4279. Min Act: -0.0000

Data Index: 71119 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4122. Min Act: -0.0000

Data Index: 467493 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1688732 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1877600 (The Pile)

Max Activating Token Index: 912

Text #17

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.3958. Min Act: -0.0000

Data Index: 645094 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4044. Min Act: -0.0000

Data Index: 217638 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.6261. Min Range: -0.6261

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1683687 (The Pile)

Max Activating Token Index: 619