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

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

Neuron 3621 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.7254. Min Act: -0.0000

Data Index: 493478 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.7891. Min Act: -0.0000

Data Index: 10233 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.6861. Min Act: -0.0000

Data Index: 657002 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5644. Min Act: -0.0000

Data Index: 50389 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3921. Min Act: -0.0000

Data Index: 518022 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5357. Min Act: -0.0000

Data Index: 350025 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5501. Min Act: -0.0000

Data Index: 886728 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5240. Min Act: -0.0000

Data Index: 552965 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4649. Min Act: -0.0000

Data Index: 392702 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1021513 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1300051 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1069982 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5216. Min Act: -0.0000

Data Index: 299839 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3749. Min Act: -0.0000

Data Index: 811977 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3741. Min Act: -0.0000

Data Index: 370680 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1259837 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3633. Min Act: -0.0000

Data Index: 810113 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1093863 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3211. Min Act: -0.0000

Data Index: 146961 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.3230. Min Act: -0.0000

Data Index: 351469 (C4 (Web Text))

Max Activating Token Index: 977