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

Dataset: The Pile

Neuron 2611 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.5764. Min Act: -0.0000

Data Index: 399322 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.3562. Min Act: -0.0000

Data Index: 1432338 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.3880. Min Act: -0.0000

Data Index: 354187 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1287928 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.2491. Min Act: 0.0000

Data Index: 22877 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.2902. Min Act: -0.0000

Data Index: 1802819 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.2011. Min Act: 0.0000

Data Index: 1910838 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1988400 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.1752. Min Act: -0.0001

Data Index: 1784871 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.0970. Min Act: -0.0000

Data Index: 222710 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.1470. Min Act: -0.0000

Data Index: 480177 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.1826. Min Act: -0.0000

Data Index: 657124 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.0226. Min Act: -0.0000

Data Index: 95297 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1147719 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.0981. Min Act: -0.0000

Data Index: 386573 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.0641. Min Act: -0.0000

Data Index: 963725 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1818226 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1511513 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.0372. Min Act: 0.0000

Data Index: 1541680 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.1212. Min Act: -0.0000

Data Index: 243514 (The Pile)

Max Activating Token Index: 922