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

Dataset: The Pile

Neuron 1798 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0037. Min Range: -3.0037

Max Act: 3.0037. Min Act: -0.0000

Data Index: 1430210 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.4985. Min Act: -0.0000

Data Index: 207098 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.4075. Min Act: -0.0000

Data Index: 382644 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.3925. Min Act: -0.0000

Data Index: 433765 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.2700. Min Act: -0.0000

Data Index: 1060200 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.0299. Min Act: -0.0000

Data Index: 495436 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.3668. Min Act: -0.0000

Data Index: 632217 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.2345. Min Act: -0.0000

Data Index: 1722256 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.1042. Min Act: -0.0000

Data Index: 601260 (The Pile)

Max Activating Token Index: 628

Text #9

Max Range: 3.0037. Min Range: -3.0037

Max Act: 1.9873. Min Act: -0.0000

Data Index: 668697 (The Pile)

Max Activating Token Index: 571

Text #10

Max Range: 3.0037. Min Range: -3.0037

Max Act: 1.9529. Min Act: -0.0000

Data Index: 1109653 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.1151. Min Act: -0.0000

Data Index: 334061 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.2587. Min Act: -0.0000

Data Index: 680018 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.1508. Min Act: -0.0000

Data Index: 1859428 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 3.0037. Min Range: -3.0037

Max Act: 2.0065. Min Act: -0.0000

Data Index: 654594 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 3.0037. Min Range: -3.0037

Max Act: 1.6905. Min Act: -0.0000

Data Index: 1342251 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 3.0037. Min Range: -3.0037

Max Act: 1.9521. Min Act: -0.0000

Data Index: 1110737 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 3.0037. Min Range: -3.0037

Max Act: 1.9109. Min Act: -0.0000

Data Index: 1254918 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 3.0037. Min Range: -3.0037

Max Act: 1.7989. Min Act: -0.0000

Data Index: 1818475 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 3.0037. Min Range: -3.0037

Max Act: 1.7913. Min Act: -0.0000

Data Index: 1800869 (The Pile)

Max Activating Token Index: 570