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

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

Neuron 1662 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3728. Min Act: -0.0001

Data Index: 823200 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3552. Min Act: -0.0001

Data Index: 97476 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3316. Min Act: -0.0001

Data Index: 415188 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3033. Min Act: -0.0001

Data Index: 754545 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3189. Min Act: -0.0001

Data Index: 240625 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2975. Min Act: -0.0001

Data Index: 129855 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2764. Min Act: -0.0001

Data Index: 111914 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.3025. Min Act: -0.0001

Data Index: 346954 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1213130 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2916. Min Act: -0.0001

Data Index: 23614 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2882. Min Act: -0.0001

Data Index: 68509 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2819. Min Act: -0.0001

Data Index: 254430 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2877. Min Act: -0.0001

Data Index: 1107267 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2544. Min Act: -0.0001

Data Index: 413892 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2699. Min Act: -0.0001

Data Index: 472142 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2589. Min Act: -0.0001

Data Index: 1161380 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2435. Min Act: -0.0001

Data Index: 386799 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2664. Min Act: -0.0001

Data Index: 283536 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2553. Min Act: -0.0001

Data Index: 236069 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.3728. Min Range: -0.3728

Max Act: 0.2696. Min Act: -0.0001

Data Index: 145866 (C4 (Web Text))

Max Activating Token Index: 437