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

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

Neuron 5723 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1311. Min Range: -6.1311

Max Act: 6.1311. Min Act: -0.0000

Data Index: 183662 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 6.1311. Min Range: -6.1311

Max Act: 4.7197. Min Act: -0.0000

Data Index: 1159627 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 6.1311. Min Range: -6.1311

Max Act: 4.0526. Min Act: -0.0000

Data Index: 396850 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.5567. Min Act: -0.0000

Data Index: 841545 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 6.1311. Min Range: -6.1311

Max Act: 4.5634. Min Act: -0.0000

Data Index: 1217742 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 6.1311. Min Range: -6.1311

Max Act: 4.3077. Min Act: -0.0000

Data Index: 1146972 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 6.1311. Min Range: -6.1311

Max Act: 4.1105. Min Act: -0.0000

Data Index: 310471 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 6.1311. Min Range: -6.1311

Max Act: 4.0857. Min Act: -0.0000

Data Index: 948175 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 6.1311. Min Range: -6.1311

Max Act: 4.3661. Min Act: -0.0000

Data Index: 1015036 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 6.1311. Min Range: -6.1311

Max Act: 4.1486. Min Act: -0.0000

Data Index: 143565 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.7608. Min Act: -0.0000

Data Index: 818644 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.7061. Min Act: -0.0000

Data Index: 1219329 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.5827. Min Act: -0.0000

Data Index: 976677 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.8833. Min Act: -0.0000

Data Index: 1198252 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.5049. Min Act: -0.0000

Data Index: 705752 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.2489. Min Act: -0.0000

Data Index: 675438 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.7262. Min Act: -0.0000

Data Index: 884617 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.2847. Min Act: -0.0000

Data Index: 970628 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.7283. Min Act: -0.0000

Data Index: 1246496 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 6.1311. Min Range: -6.1311

Max Act: 3.6906. Min Act: -0.0000

Data Index: 1119910 (C4 (Web Text))

Max Activating Token Index: 521