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

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

Neuron 3495 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1074125 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3923. Min Act: -0.0001

Data Index: 1521242 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3246. Min Act: -0.0001

Data Index: 1176319 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3344. Min Act: -0.0001

Data Index: 336503 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3055. Min Act: -0.0000

Data Index: 71761 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3412. Min Act: -0.0000

Data Index: 160658 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3176. Min Act: -0.0001

Data Index: 6381 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1002632 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3193. Min Act: -0.0001

Data Index: 324521 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1207124 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2763. Min Act: -0.0001

Data Index: 517871 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1521601 (Python Code)

Max Activating Token Index: 944

Text #12

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2714. Min Act: -0.0001

Data Index: 1582143 (Python Code)

Max Activating Token Index: 411

Text #13

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2736. Min Act: -0.0000

Data Index: 789657 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2762. Min Act: -0.0000

Data Index: 420700 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2759. Min Act: -0.0001

Data Index: 263109 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2638. Min Act: -0.0001

Data Index: 10681 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1368117 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1648633 (Python Code)

Max Activating Token Index: 578

Text #19

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2696. Min Act: -0.0001

Data Index: 488097 (C4 (Web Text))

Max Activating Token Index: 299