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

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

Neuron 1482 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: 0.7484. Min Range: -0.7484

Max Act: 0.7484. Min Act: -0.0000

Data Index: 733544 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6923. Min Act: -0.0000

Data Index: 956099 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6638. Min Act: -0.0000

Data Index: 200010 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6624. Min Act: -0.0000

Data Index: 703640 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6507. Min Act: -0.0000

Data Index: 558787 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6830. Min Act: -0.0000

Data Index: 586138 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6354. Min Act: -0.0000

Data Index: 347299 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6326. Min Act: -0.0000

Data Index: 218584 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1007134 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6290. Min Act: -0.0000

Data Index: 68297 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6133. Min Act: -0.0000

Data Index: 809401 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6002. Min Act: -0.0000

Data Index: 843919 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5807. Min Act: -0.0000

Data Index: 107164 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5511. Min Act: -0.0000

Data Index: 618249 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1334167 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5463. Min Act: -0.0000

Data Index: 125833 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1304994 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5323. Min Act: -0.0000

Data Index: 782701 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5612. Min Act: -0.0000

Data Index: 134720 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1340144 (C4 (Web Text))

Max Activating Token Index: 212