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

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

Neuron 1195 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.5873. Min Act: -0.0000

Data Index: 500040 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.3284. Min Act: -0.0000

Data Index: 1252457 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1578783 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.2891. Min Act: -0.0000

Data Index: 655337 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1378460 (Python Code)

Max Activating Token Index: 793

Text #5

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1071061 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.1364. Min Act: -0.0000

Data Index: 986672 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.1041. Min Act: -0.0000

Data Index: 819810 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1417486 (Python Code)

Max Activating Token Index: 1010

Text #9

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.0046. Min Act: -0.0000

Data Index: 197665 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 1.5873. Min Range: -1.5873

Max Act: 1.0450. Min Act: -0.0000

Data Index: 871812 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9871. Min Act: -0.0000

Data Index: 413135 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8858. Min Act: -0.0000

Data Index: 936353 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8938. Min Act: -0.0000

Data Index: 184219 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8874. Min Act: -0.0000

Data Index: 499753 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1449974 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.9261. Min Act: -0.0000

Data Index: 806996 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8594. Min Act: -0.0000

Data Index: 314573 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8685. Min Act: -0.0000

Data Index: 231261 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.5873. Min Range: -1.5873

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1060491 (C4 (Web Text))

Max Activating Token Index: 712