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

Dataset: The Pile

Neuron 1161 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: 1.0132. Min Range: -1.0132

Max Act: 1.0132. Min Act: -0.0000

Data Index: 504414 (The Pile)

Max Activating Token Index: 799

Text #1

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1711443 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1528485 (The Pile)

Max Activating Token Index: 56

Text #3

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1815372 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.7455. Min Act: -0.0000

Data Index: 380390 (The Pile)

Max Activating Token Index: 699

Text #5

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6531. Min Act: -0.0000

Data Index: 459057 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1136654 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6471. Min Act: -0.0000

Data Index: 804706 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6595. Min Act: -0.0000

Data Index: 178579 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6288. Min Act: -0.0000

Data Index: 392 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1263503 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6867. Min Act: -0.0000

Data Index: 80640 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6384. Min Act: -0.0000

Data Index: 135220 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.5929. Min Act: -0.0000

Data Index: 952954 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6092. Min Act: -0.0000

Data Index: 584797 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1139307 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6393. Min Act: -0.0000

Data Index: 965918 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1093360 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.5964. Min Act: -0.0000

Data Index: 830939 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 1.0132. Min Range: -1.0132

Max Act: 0.5836. Min Act: -0.0000

Data Index: 549494 (The Pile)

Max Activating Token Index: 828