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

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

Neuron 4518 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0675. Min Range: -1.0675

Max Act: 1.0675. Min Act: -0.0001

Data Index: 896220 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.7790. Min Act: -0.0001

Data Index: 653194 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.7418. Min Act: -0.0001

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.7324. Min Act: -0.0001

Data Index: 1588106 (Python Code)

Max Activating Token Index: 330

Text #4

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.7777. Min Act: -0.0001

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.7104. Min Act: -0.0001

Data Index: 290261 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.7007. Min Act: -0.0001

Data Index: 841597 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6760. Min Act: -0.0001

Data Index: 442533 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6747. Min Act: -0.0001

Data Index: 1196182 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6144. Min Act: -0.0001

Data Index: 843666 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6374. Min Act: -0.0001

Data Index: 535860 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6320. Min Act: -0.0001

Data Index: 351864 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6156. Min Act: -0.0001

Data Index: 1474261 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6333. Min Act: -0.0001

Data Index: 1078671 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6738. Min Act: -0.0001

Data Index: 1330880 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6070. Min Act: -0.0001

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.5821. Min Act: -0.0001

Data Index: 405422 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6408. Min Act: -0.0001

Data Index: 176195 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.5593. Min Act: -0.0001

Data Index: 277049 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.6008. Min Act: -0.0001

Data Index: 836296 (C4 (Web Text))

Max Activating Token Index: 508