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

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

Neuron 2403 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.5821. Min Act: -0.0000

Data Index: 745577 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.1943. Min Act: -0.0000

Data Index: 628516 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.1042. Min Act: -0.0000

Data Index: 709120 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.9791. Min Act: -0.0000

Data Index: 278288 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1308862 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1008540 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.9022. Min Act: -0.0000

Data Index: 412512 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.8772. Min Act: -0.0000

Data Index: 710118 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.7967. Min Act: -0.0000

Data Index: 112064 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.7701. Min Act: -0.0000

Data Index: 321693 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1218307 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.7289. Min Act: -0.0000

Data Index: 500621 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.6557. Min Act: -0.0000

Data Index: 288892 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1321128 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.6522. Min Act: -0.0000

Data Index: 473598 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.6830. Min Act: -0.0000

Data Index: 255758 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1014094 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.6689. Min Act: -0.0000

Data Index: 199713 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.6434. Min Act: -0.0000

Data Index: 434123 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 1.5821. Min Range: -1.5821

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1082893 (C4 (Web Text))

Max Activating Token Index: 818