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

Dataset: The Pile

Neuron 2763 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: 1.4611. Min Range: -1.4611

Max Act: 1.4611. Min Act: -0.0000

Data Index: 714046 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.2768. Min Act: -0.0000

Data Index: 746324 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1465700 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.1448. Min Act: -0.0000

Data Index: 1752903 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.1154. Min Act: -0.0000

Data Index: 445868 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1617984 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9674. Min Act: -0.0000

Data Index: 900986 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9525. Min Act: -0.0000

Data Index: 152590 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1955562 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.0314. Min Act: -0.0000

Data Index: 796860 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1168134 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9611. Min Act: -0.0000

Data Index: 944933 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9493. Min Act: -0.0000

Data Index: 490850 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1304861 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9986. Min Act: -0.0000

Data Index: 567604 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1254264 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9288. Min Act: -0.0000

Data Index: 799637 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.0217. Min Act: -0.0000

Data Index: 227308 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1731343 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9067. Min Act: -0.0000

Data Index: 277302 (The Pile)

Max Activating Token Index: 655