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

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

Neuron 4840 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: 0.6885. Min Range: -0.6885

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1067329 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6885. Min Act: -0.0000

Data Index: 535265 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6555. Min Act: -0.0000

Data Index: 580383 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6434. Min Act: -0.0000

Data Index: 159866 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6426. Min Act: -0.0000

Data Index: 735633 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6404. Min Act: -0.0000

Data Index: 16098 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1241602 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6310. Min Act: -0.0000

Data Index: 890524 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6342. Min Act: -0.0000

Data Index: 161256 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6252. Min Act: -0.0000

Data Index: 460296 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1237864 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6435. Min Act: -0.0000

Data Index: 877777 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6613. Min Act: -0.0000

Data Index: 921527 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6011. Min Act: -0.0000

Data Index: 457960 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6178. Min Act: -0.0000

Data Index: 371153 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6132. Min Act: -0.0000

Data Index: 557002 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6262. Min Act: -0.0000

Data Index: 849484 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6142. Min Act: -0.0000

Data Index: 258937 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1334655 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.6885. Min Range: -0.6885

Max Act: 0.6478. Min Act: -0.0000

Data Index: 255583 (C4 (Web Text))

Max Activating Token Index: 317