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

Dataset: The Pile

Neuron 3989 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.6300. Min Act: -0.0000

Data Index: 672019 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4297. Min Act: -0.0000

Data Index: 533053 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.5972. Min Act: -0.0000

Data Index: 358906 (The Pile)

Max Activating Token Index: 921

Text #3

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1041668 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1833729 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.2685. Min Act: -0.0000

Data Index: 357602 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1293025 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1220362 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1177330 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.5884. Min Act: -0.0000

Data Index: 622381 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3048. Min Act: -0.0000

Data Index: 978694 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3431. Min Act: -0.0000

Data Index: 790423 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1353709 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1035238 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1114257 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4100. Min Act: -0.0000

Data Index: 969465 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3446. Min Act: -0.0000

Data Index: 204092 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3675. Min Act: -0.0000

Data Index: 130193 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1974477 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 0.6300. Min Range: -0.6300

Max Act: 0.3482. Min Act: -0.0000

Data Index: 562799 (The Pile)

Max Activating Token Index: 644