Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1252 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.4573. Min Act: 0.0000

Data Index: 88598 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1032436 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.3697. Min Act: -0.0000

Data Index: 912411 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.3195. Min Act: -0.0000

Data Index: 697386 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1035002 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.1508. Min Act: -0.0000

Data Index: 932331 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.0557. Min Act: -0.0000

Data Index: 698640 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.1140. Min Act: -0.0000

Data Index: 358529 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.0797. Min Act: 0.0000

Data Index: 792655 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.1337. Min Act: -0.0000

Data Index: 448023 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.0282. Min Act: -0.0000

Data Index: 817642 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.5044. Min Range: -1.5044

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1073522 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1155741 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.0342. Min Act: -0.0000

Data Index: 327774 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.5044. Min Range: -1.5044

Max Act: 1.0212. Min Act: -0.0000

Data Index: 525414 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.5044. Min Range: -1.5044

Max Act: 0.8528. Min Act: -0.0000

Data Index: 895002 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 1.5044. Min Range: -1.5044

Max Act: 0.8859. Min Act: -0.0000

Data Index: 727103 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.5044. Min Range: -1.5044

Max Act: 0.8413. Min Act: -0.0000

Data Index: 705522 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 1.5044. Min Range: -1.5044

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1214502 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.5044. Min Range: -1.5044

Max Act: 0.8577. Min Act: -0.0000

Data Index: 415007 (C4 (Web Text))

Max Activating Token Index: 506