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

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

Neuron 560 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.1425. Min Act: -0.0001

Data Index: 914842 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.2726. Min Act: -0.0001

Data Index: 1086001 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0624. Min Act: -0.0001

Data Index: 838792 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.2726. Min Range: -1.2726

Max Act: 1.0620. Min Act: -0.0001

Data Index: 104542 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9641. Min Act: -0.0001

Data Index: 617361 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9666. Min Act: -0.0001

Data Index: 95676 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9645. Min Act: -0.0001

Data Index: 488058 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9458. Min Act: -0.0001

Data Index: 1353074 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.8814. Min Act: -0.0001

Data Index: 328504 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9266. Min Act: -0.0001

Data Index: 126774 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9142. Min Act: -0.0001

Data Index: 364532 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.8558. Min Act: -0.0001

Data Index: 1140086 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9237. Min Act: -0.0001

Data Index: 945055 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9057. Min Act: -0.0001

Data Index: 1129886 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9194. Min Act: -0.0001

Data Index: 1104133 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9257. Min Act: -0.0001

Data Index: 297081 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.8927. Min Act: -0.0001

Data Index: 30212 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.8304. Min Act: -0.0001

Data Index: 661297 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.8610. Min Act: -0.0001

Data Index: 47651 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.2726. Min Range: -1.2726

Max Act: 0.9090. Min Act: -0.0001

Data Index: 741768 (C4 (Web Text))

Max Activating Token Index: 166