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

Dataset: The Pile

Neuron 1171 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.4877. Min Act: -0.0000

Data Index: 1522412 (The Pile)

Max Activating Token Index: 512

Text #1

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.5189. Min Act: -0.0000

Data Index: 937750 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.9909. Min Act: -0.0000

Data Index: 55800 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.9969. Min Act: -0.0000

Data Index: 809536 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 4.5189. Min Range: -4.5189

Max Act: 4.0660. Min Act: -0.0000

Data Index: 1524741 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.7326. Min Act: -0.0000

Data Index: 1449575 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.7965. Min Act: -0.0000

Data Index: 1260317 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.4155. Min Act: -0.0000

Data Index: 622159 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.3796. Min Act: -0.0000

Data Index: 1657603 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.6715. Min Act: -0.0000

Data Index: 1231028 (The Pile)

Max Activating Token Index: 249

Text #10

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.6153. Min Act: -0.0000

Data Index: 927844 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.3263. Min Act: -0.0000

Data Index: 1519457 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.4584. Min Act: -0.0000

Data Index: 972179 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.4408. Min Act: -0.0000

Data Index: 253363 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.4143. Min Act: -0.0000

Data Index: 1636364 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.4064. Min Act: -0.0000

Data Index: 1907733 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.4054. Min Act: -0.0000

Data Index: 667788 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.5491. Min Act: -0.0000

Data Index: 1149047 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.3921. Min Act: -0.0000

Data Index: 271558 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 4.5189. Min Range: -4.5189

Max Act: 3.3895. Min Act: -0.0000

Data Index: 458017 (The Pile)

Max Activating Token Index: 34