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

Dataset: The Pile

Neuron 2814 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.0753. Min Range: -3.0753

Max Act: 3.0590. Min Act: -0.0000

Data Index: 1883954 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9327. Min Act: -0.0000

Data Index: 1113377 (The Pile)

Max Activating Token Index: 117

Text #2

Max Range: 3.0753. Min Range: -3.0753

Max Act: 3.0637. Min Act: -0.0000

Data Index: 1295824 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.7505. Min Act: -0.0000

Data Index: 1629811 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.9722. Min Act: -0.0000

Data Index: 1624609 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.8166. Min Act: -0.0000

Data Index: 575927 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.8995. Min Act: -0.0000

Data Index: 1951811 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.8453. Min Act: -0.0000

Data Index: 933923 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.7237. Min Act: -0.0000

Data Index: 3839 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 3.0753. Min Range: -3.0753

Max Act: 3.0753. Min Act: -0.0000

Data Index: 1344225 (The Pile)

Max Activating Token Index: 671

Text #10

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.5605. Min Act: -0.0000

Data Index: 1333153 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.5708. Min Act: -0.0000

Data Index: 1748001 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.4421. Min Act: -0.0000

Data Index: 1463872 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.5509. Min Act: -0.0000

Data Index: 1103169 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.4937. Min Act: -0.0000

Data Index: 1318866 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.6051. Min Act: -0.0000

Data Index: 514189 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.5982. Min Act: -0.0000

Data Index: 583199 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.4110. Min Act: -0.0000

Data Index: 585516 (The Pile)

Max Activating Token Index: 438

Text #18

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.5276. Min Act: -0.0000

Data Index: 1901820 (The Pile)

Max Activating Token Index: 548

Text #19

Max Range: 3.0753. Min Range: -3.0753

Max Act: 2.4066. Min Act: -0.0000

Data Index: 375987 (The Pile)

Max Activating Token Index: 339