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

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

Neuron 2436 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1998. Min Act: -0.0001

Data Index: 995764 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1428. Min Act: -0.0001

Data Index: 297514 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0560. Min Act: -0.0001

Data Index: 38462 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0365. Min Act: -0.0001

Data Index: 1208137 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9785. Min Act: -0.0001

Data Index: 800747 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9234. Min Act: -0.0001

Data Index: 411048 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9439. Min Act: -0.0001

Data Index: 1035239 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9644. Min Act: -0.0001

Data Index: 692473 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9274. Min Act: -0.0001

Data Index: 36158 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9580. Min Act: -0.0001

Data Index: 469299 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9228. Min Act: -0.0001

Data Index: 332818 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8814. Min Act: -0.0001

Data Index: 458296 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9001. Min Act: -0.0001

Data Index: 206898 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8764. Min Act: -0.0001

Data Index: 333115 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8957. Min Act: -0.0001

Data Index: 536451 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8860. Min Act: -0.0001

Data Index: 1035507 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8213. Min Act: -0.0001

Data Index: 1251307 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8748. Min Act: -0.0001

Data Index: 1326137 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8415. Min Act: -0.0001

Data Index: 304559 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8778. Min Act: -0.0001

Data Index: 447538 (C4 (Web Text))

Max Activating Token Index: 123