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

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

Neuron 2556 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4840. Min Range: -2.4840

Max Act: 2.4840. Min Act: -0.0000

Data Index: 778747 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 2.4840. Min Range: -2.4840

Max Act: 2.1784. Min Act: -0.0000

Data Index: 1180744 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 2.4840. Min Range: -2.4840

Max Act: 2.1419. Min Act: -0.0000

Data Index: 247361 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 2.4840. Min Range: -2.4840

Max Act: 2.0890. Min Act: -0.0000

Data Index: 1095826 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.9549. Min Act: -0.0000

Data Index: 453106 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 2.4840. Min Range: -2.4840

Max Act: 2.1224. Min Act: -0.0000

Data Index: 762097 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 2.4840. Min Range: -2.4840

Max Act: 2.1107. Min Act: -0.0000

Data Index: 985090 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.8235. Min Act: -0.0000

Data Index: 84247 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.8717. Min Act: -0.0000

Data Index: 32947 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.8147. Min Act: -0.0000

Data Index: 1284005 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.9005. Min Act: -0.0000

Data Index: 557435 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.6491. Min Act: -0.0000

Data Index: 541622 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.6867. Min Act: -0.0000

Data Index: 769338 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.6775. Min Act: -0.0000

Data Index: 1345583 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1289468 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.5205. Min Act: -0.0000

Data Index: 245594 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1026999 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1275014 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.5971. Min Act: -0.0000

Data Index: 495848 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 2.4840. Min Range: -2.4840

Max Act: 1.5735. Min Act: -0.0000

Data Index: 730085 (C4 (Web Text))

Max Activating Token Index: 387