Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4035 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.4696. Min Act: -0.0000

Data Index: 213802 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.4510. Min Act: -0.0000

Data Index: 454495 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3664. Min Act: -0.0000

Data Index: 982555 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.5066. Min Act: -0.0000

Data Index: 1392703 (Python Code)

Max Activating Token Index: 463

Text #4

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3200. Min Act: -0.0000

Data Index: 339927 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3879. Min Act: -0.0000

Data Index: 391520 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1074979 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3646. Min Act: -0.0000

Data Index: 707533 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.4480. Min Act: -0.0000

Data Index: 413452 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.4226. Min Act: -0.0000

Data Index: 1028331 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2518. Min Act: -0.0000

Data Index: 938612 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1145448 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1297581 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1200195 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2997. Min Act: -0.0000

Data Index: 961077 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3884. Min Act: -0.0000

Data Index: 520607 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3664. Min Act: -0.0000

Data Index: 864471 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2860. Min Act: -0.0000

Data Index: 846120 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3457. Min Act: -0.0000

Data Index: 1232376 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.1533. Min Act: -0.0000

Data Index: 963166 (C4 (Web Text))

Max Activating Token Index: 706