Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 619 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.2431. Min Act: -0.0000

Data Index: 113609 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.2505. Min Act: -0.0000

Data Index: 947797 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1191544 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1277456 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0059. Min Act: -0.0000

Data Index: 374964 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9347. Min Act: -0.0000

Data Index: 822647 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9646. Min Act: -0.0000

Data Index: 771780 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 1.2505. Min Range: -1.2505

Max Act: 1.0130. Min Act: -0.0000

Data Index: 809489 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1133677 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9236. Min Act: -0.0000

Data Index: 603273 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1143887 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9564. Min Act: -0.0000

Data Index: 383754 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9068. Min Act: -0.0000

Data Index: 574822 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9310. Min Act: -0.0000

Data Index: 754879 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.8362. Min Act: -0.0000

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9193. Min Act: -0.0000

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9184. Min Act: -0.0000

Data Index: 386437 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9002. Min Act: -0.0001

Data Index: 668557 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.8969. Min Act: -0.0000

Data Index: 119341 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.2505. Min Range: -1.2505

Max Act: 0.9115. Min Act: -0.0000

Data Index: 633564 (C4 (Web Text))

Max Activating Token Index: 220