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

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

Neuron 2855 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: 0.3328. Min Range: -0.3328

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1559261 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.3095. Min Act: -0.0000

Data Index: 224743 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1290810 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1024295 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2939. Min Act: -0.0001

Data Index: 954233 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1005086 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2746. Min Act: -0.0001

Data Index: 5527 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2753. Min Act: -0.0000

Data Index: 217341 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2878. Min Act: -0.0001

Data Index: 1456046 (Python Code)

Max Activating Token Index: 987

Text #9

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2735. Min Act: -0.0001

Data Index: 1370868 (Python Code)

Max Activating Token Index: 350

Text #10

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2829. Min Act: -0.0000

Data Index: 57062 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2787. Min Act: -0.0000

Data Index: 660868 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2664. Min Act: -0.0001

Data Index: 912672 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2564. Min Act: -0.0000

Data Index: 864504 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2601. Min Act: -0.0000

Data Index: 198155 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1324760 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2514. Min Act: -0.0001

Data Index: 722993 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2457. Min Act: -0.0001

Data Index: 163632 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2517. Min Act: -0.0001

Data Index: 1318556 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2588. Min Act: -0.0000

Data Index: 30464 (C4 (Web Text))

Max Activating Token Index: 925