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

Dataset: The Pile

Neuron 1428 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1256371 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5953. Min Act: -0.0000

Data Index: 393096 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1329924 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1868078 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4896. Min Act: -0.0000

Data Index: 513810 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4188. Min Act: -0.0000

Data Index: 362037 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1510146 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1759215 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1257571 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1206517 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1744953 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3447. Min Act: -0.0000

Data Index: 561900 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3954. Min Act: -0.0000

Data Index: 753212 (The Pile)

Max Activating Token Index: 950

Text #13

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1610809 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3866. Min Act: 0.0000

Data Index: 179882 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4064. Min Act: -0.0000

Data Index: 988089 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1363816 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3858. Min Act: -0.0000

Data Index: 146063 (The Pile)

Max Activating Token Index: 739

Text #18

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1834612 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 0.6375. Min Range: -0.6375

Max Act: 0.3681. Min Act: 0.0000

Data Index: 493557 (The Pile)

Max Activating Token Index: 263