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

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

Neuron 1835 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: 0.3857. Min Range: -0.3857

Max Act: 0.3857. Min Act: -0.0000

Data Index: 457085 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.3308. Min Act: -0.0000

Data Index: 272315 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1352151 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2648. Min Act: -0.0000

Data Index: 88821 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2662. Min Act: -0.0000

Data Index: 784488 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1303263 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2674. Min Act: -0.0000

Data Index: 864641 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2618. Min Act: -0.0000

Data Index: 664298 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2297. Min Act: -0.0001

Data Index: 986076 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2540. Min Act: -0.0001

Data Index: 226145 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2646. Min Act: -0.0001

Data Index: 137676 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2381. Min Act: -0.0000

Data Index: 285213 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1216084 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2535. Min Act: -0.0000

Data Index: 12045 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2520. Min Act: -0.0001

Data Index: 863316 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1263383 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2827. Min Act: -0.0001

Data Index: 41446 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1099352 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2367. Min Act: -0.0001

Data Index: 28935 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.3857. Min Range: -0.3857

Max Act: 0.2536. Min Act: -0.0000

Data Index: 209375 (C4 (Web Text))

Max Activating Token Index: 286