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

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

Neuron 3958 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: 0.3617. Min Range: -0.3617

Max Act: 0.3358. Min Act: -0.0000

Data Index: 132616 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1281791 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.3617. Min Act: -0.0000

Data Index: 31636 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.3197. Min Act: -0.0000

Data Index: 329450 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.3037. Min Act: -0.0000

Data Index: 57836 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.3163. Min Act: -0.0000

Data Index: 776427 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.3034. Min Act: -0.0000

Data Index: 800154 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.2877. Min Act: -0.0001

Data Index: 1248936 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.2906. Min Act: -0.0001

Data Index: 937887 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1357543 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.2527. Min Act: -0.0001

Data Index: 649751 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1036897 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.2256. Min Act: -0.0000

Data Index: 622190 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.2126. Min Act: -0.0000

Data Index: 510287 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.2137. Min Act: -0.0001

Data Index: 119572 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.1994. Min Act: -0.0001

Data Index: 786335 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.1732. Min Act: -0.0001

Data Index: 450310 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1178271 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1620769 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 0.3617. Min Range: -0.3617

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1328894 (C4 (Web Text))

Max Activating Token Index: 849