Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1774 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.4098. Min Act: -0.0001

Data Index: 709120 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.4037. Min Act: -0.0001

Data Index: 417057 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.4067. Min Act: -0.0001

Data Index: 455097 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3860. Min Act: -0.0001

Data Index: 664622 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3784. Min Act: -0.0001

Data Index: 855556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3715. Min Act: -0.0001

Data Index: 746413 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3625. Min Act: -0.0001

Data Index: 1080846 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3578. Min Act: -0.0001

Data Index: 366365 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3653. Min Act: -0.0001

Data Index: 372499 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3545. Min Act: -0.0001

Data Index: 392878 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3529. Min Act: -0.0001

Data Index: 60338 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3567. Min Act: -0.0001

Data Index: 203814 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3550. Min Act: -0.0001

Data Index: 41686 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3502. Min Act: -0.0001

Data Index: 137882 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1290945 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3509. Min Act: -0.0002

Data Index: 743285 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3569. Min Act: -0.0001

Data Index: 251704 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3502. Min Act: -0.0001

Data Index: 1268410 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3477. Min Act: -0.0001

Data Index: 518031 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.4098. Min Range: -0.4098

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1247197 (C4 (Web Text))

Max Activating Token Index: 888