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

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

Neuron 1726 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: 1.0684. Min Range: -1.0684

Max Act: 1.0684. Min Act: -0.0001

Data Index: 1511703 (Python Code)

Max Activating Token Index: 333

Text #1

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8853. Min Act: -0.0001

Data Index: 1566489 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8086. Min Act: -0.0001

Data Index: 781816 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8350. Min Act: -0.0001

Data Index: 1092417 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.7554. Min Act: -0.0001

Data Index: 60522 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8774. Min Act: -0.0001

Data Index: 1528703 (Python Code)

Max Activating Token Index: 705

Text #6

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8186. Min Act: -0.0001

Data Index: 1439433 (Python Code)

Max Activating Token Index: 731

Text #7

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8025. Min Act: -0.0001

Data Index: 1583279 (Python Code)

Max Activating Token Index: 470

Text #8

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8156. Min Act: -0.0001

Data Index: 1388773 (Python Code)

Max Activating Token Index: 409

Text #9

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8286. Min Act: -0.0001

Data Index: 1564975 (Python Code)

Max Activating Token Index: 847

Text #10

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.7734. Min Act: -0.0001

Data Index: 1469798 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8231. Min Act: -0.0001

Data Index: 1597545 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.8125. Min Act: -0.0001

Data Index: 1381612 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.7394. Min Act: -0.0001

Data Index: 1625703 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.7155. Min Act: -0.0001

Data Index: 545961 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1582303 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.6674. Min Act: -0.0001

Data Index: 677148 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.6884. Min Act: -0.0001

Data Index: 317406 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.6428. Min Act: -0.0001

Data Index: 1418062 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.7252. Min Act: -0.0001

Data Index: 1502637 (Python Code)

Max Activating Token Index: 332