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

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

Neuron 3242 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: 0.1737. Min Range: -0.1737

Max Act: 0.1737. Min Act: -0.0000

Data Index: 663610 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1451. Min Act: -0.0000

Data Index: 118048 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1266. Min Act: -0.0000

Data Index: 531886 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1299. Min Act: -0.0000

Data Index: 244844 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1160. Min Act: -0.0000

Data Index: 368747 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1211. Min Act: -0.0000

Data Index: 159512 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1082. Min Act: -0.0000

Data Index: 424927 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1050. Min Act: -0.0000

Data Index: 856574 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1104. Min Act: -0.0001

Data Index: 366636 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1154. Min Act: -0.0000

Data Index: 992660 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1008. Min Act: -0.0000

Data Index: 722016 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1018. Min Act: -0.0000

Data Index: 252079 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1017. Min Act: -0.0000

Data Index: 417910 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1015. Min Act: -0.0001

Data Index: 446919 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0983. Min Act: -0.0000

Data Index: 814029 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0965. Min Act: -0.0000

Data Index: 273467 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0963. Min Act: -0.0000

Data Index: 717585 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1064. Min Act: -0.0000

Data Index: 425730 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0981. Min Act: -0.0000

Data Index: 119678 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0951. Min Act: -0.0000

Data Index: 668701 (C4 (Web Text))

Max Activating Token Index: 805