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

Dataset: The Pile

Neuron 1936 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1109. Min Range: -2.1109

Max Act: 2.1109. Min Act: -0.0001

Data Index: 306308 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8993. Min Act: -0.0001

Data Index: 1053059 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8538. Min Act: -0.0001

Data Index: 1988880 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8207. Min Act: -0.0001

Data Index: 1529652 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8393. Min Act: -0.0001

Data Index: 1225929 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8291. Min Act: -0.0001

Data Index: 386079 (The Pile)

Max Activating Token Index: 713

Text #6

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7891. Min Act: -0.0001

Data Index: 1572016 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7068. Min Act: -0.0001

Data Index: 1688341 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8348. Min Act: -0.0001

Data Index: 393843 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8405. Min Act: -0.0001

Data Index: 58345 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7729. Min Act: -0.0001

Data Index: 1247871 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8086. Min Act: -0.0001

Data Index: 735393 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8999. Min Act: -0.0001

Data Index: 1972837 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8491. Min Act: -0.0001

Data Index: 166058 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7028. Min Act: -0.0001

Data Index: 895253 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8093. Min Act: -0.0001

Data Index: 1234090 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.6232. Min Act: -0.0001

Data Index: 1567118 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.7210. Min Act: -0.0001

Data Index: 1576451 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.8124. Min Act: -0.0001

Data Index: 1667713 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 2.1109. Min Range: -2.1109

Max Act: 1.6972. Min Act: -0.0001

Data Index: 1763075 (The Pile)

Max Activating Token Index: 608