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

Dataset: The Pile

Neuron 3694 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: 1.4491. Min Range: -1.4491

Max Act: 1.4491. Min Act: -0.0000

Data Index: 996299 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.3234. Min Act: -0.0000

Data Index: 177486 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.3347. Min Act: -0.0000

Data Index: 877603 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1341575 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.3100. Min Act: -0.0000

Data Index: 216520 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2787. Min Act: -0.0000

Data Index: 765069 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.3499. Min Act: -0.0000

Data Index: 210060 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2962. Min Act: -0.0000

Data Index: 122681 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1653013 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1874. Min Act: -0.0000

Data Index: 767167 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.3510. Min Act: -0.0000

Data Index: 994841 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1663233 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1727. Min Act: -0.0000

Data Index: 660852 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1465254 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1361102 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1970. Min Act: -0.0000

Data Index: 129841 (The Pile)

Max Activating Token Index: 961

Text #16

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2703. Min Act: -0.0000

Data Index: 26853 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1240452 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1947. Min Act: -0.0000

Data Index: 126270 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2784. Min Act: -0.0000

Data Index: 1355697 (The Pile)

Max Activating Token Index: 954