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

Dataset: The Pile

Neuron 193 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: 3.0154. Min Range: -3.0154

Max Act: 2.7866. Min Act: -0.0000

Data Index: 1242494 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 3.0154. Min Range: -3.0154

Max Act: 3.0154. Min Act: -0.0000

Data Index: 953170 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.4419. Min Act: -0.0000

Data Index: 495478 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.6482. Min Act: -0.0000

Data Index: 1149053 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.6373. Min Act: -0.0000

Data Index: 1783246 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.4839. Min Act: -0.0000

Data Index: 752988 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.3786. Min Act: -0.0000

Data Index: 1258174 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 3.0154. Min Range: -3.0154

Max Act: 1.9395. Min Act: -0.0000

Data Index: 649410 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.1401. Min Act: -0.0000

Data Index: 370809 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 3.0154. Min Range: -3.0154

Max Act: 1.8791. Min Act: -0.0000

Data Index: 579601 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1567576 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.1395. Min Act: -0.0000

Data Index: 1110261 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 3.0154. Min Range: -3.0154

Max Act: 1.8866. Min Act: -0.0000

Data Index: 989901 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.2100. Min Act: -0.0000

Data Index: 1246851 (The Pile)

Max Activating Token Index: 504

Text #14

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.0558. Min Act: -0.0000

Data Index: 1270249 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 3.0154. Min Range: -3.0154

Max Act: 1.8882. Min Act: -0.0000

Data Index: 43895 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.0828. Min Act: -0.0000

Data Index: 302817 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 3.0154. Min Range: -3.0154

Max Act: 1.4116. Min Act: -0.0000

Data Index: 380412 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.1550. Min Act: -0.0000

Data Index: 528549 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 3.0154. Min Range: -3.0154

Max Act: 2.0722. Min Act: -0.0000

Data Index: 124950 (The Pile)

Max Activating Token Index: 706