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

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

Neuron 2029 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6751. Min Act: -0.0000

Data Index: 482132 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6442. Min Act: -0.0000

Data Index: 23895 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5848. Min Act: -0.0000

Data Index: 313405 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4795. Min Act: -0.0000

Data Index: 725590 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1207564 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4375. Min Act: -0.0000

Data Index: 446219 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1217852 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.3593. Min Act: -0.0000

Data Index: 61603 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1141342 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4034. Min Act: -0.0000

Data Index: 287977 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.3938. Min Act: -0.0000

Data Index: 577331 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.3939. Min Act: -0.0000

Data Index: 211168 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4052. Min Act: -0.0000

Data Index: 137542 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4213. Min Act: -0.0000

Data Index: 68981 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.3795. Min Act: -0.0000

Data Index: 999593 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.3724. Min Act: -0.0000

Data Index: 689484 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4000. Min Act: -0.0000

Data Index: 143973 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.3852. Min Act: -0.0000

Data Index: 571722 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.3592. Min Act: -0.0000

Data Index: 810982 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.3432. Min Act: -0.0000

Data Index: 575713 (C4 (Web Text))

Max Activating Token Index: 388