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

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

Neuron 718 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: 0.6798. Min Range: -0.6798

Max Act: 0.6798. Min Act: -0.0001

Data Index: 614027 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6519. Min Act: -0.0001

Data Index: 431072 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1108667 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5836. Min Act: -0.0001

Data Index: 531431 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5502. Min Act: -0.0001

Data Index: 936322 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5117. Min Act: -0.0001

Data Index: 275098 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5392. Min Act: -0.0001

Data Index: 286610 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5214. Min Act: -0.0001

Data Index: 80201 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5511. Min Act: -0.0001

Data Index: 742039 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4922. Min Act: -0.0001

Data Index: 522206 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4779. Min Act: -0.0001

Data Index: 1151047 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4873. Min Act: -0.0001

Data Index: 502831 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4995. Min Act: -0.0001

Data Index: 350088 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4350. Min Act: -0.0001

Data Index: 281658 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4952. Min Act: -0.0001

Data Index: 307138 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4921. Min Act: -0.0001

Data Index: 429551 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4567. Min Act: -0.0001

Data Index: 1309029 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1111057 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4639. Min Act: -0.0001

Data Index: 985431 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4498. Min Act: -0.0001

Data Index: 114306 (C4 (Web Text))

Max Activating Token Index: 729