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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3436 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4127. Min Range: -2.4127

Max Act: 2.4127. Min Act: -0.0000

Data Index: 1100022 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.9581. Min Act: -0.0000

Data Index: 869808 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.8185. Min Act: -0.0001

Data Index: 79573 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.8715. Min Act: -0.0001

Data Index: 930454 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.7412. Min Act: -0.0001

Data Index: 118295 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.7250. Min Act: -0.0001

Data Index: 1129739 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.7686. Min Act: -0.0000

Data Index: 713283 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.8584. Min Act: -0.0000

Data Index: 731191 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.8477. Min Act: -0.0000

Data Index: 191576 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.9579. Min Act: -0.0000

Data Index: 635300 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.7166. Min Act: -0.0001

Data Index: 1006095 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.8092. Min Act: -0.0000

Data Index: 39197 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.7706. Min Act: -0.0001

Data Index: 1167538 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.6437. Min Act: -0.0001

Data Index: 1116941 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.7325. Min Act: -0.0001

Data Index: 353975 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.6692. Min Act: -0.0000

Data Index: 1311096 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.6453. Min Act: -0.0000

Data Index: 432975 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.6718. Min Act: -0.0000

Data Index: 1259754 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.6211. Min Act: -0.0001

Data Index: 38998 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.4127. Min Range: -2.4127

Max Act: 1.5321. Min Act: -0.0001

Data Index: 557002 (C4 (Web Text))

Max Activating Token Index: 262