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

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

Neuron 3808 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.7164. Min Act: -0.0000

Data Index: 522410 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6569. Min Act: -0.0000

Data Index: 121410 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6409. Min Act: -0.0000

Data Index: 811429 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5851. Min Act: -0.0000

Data Index: 349564 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6450. Min Act: -0.0000

Data Index: 711629 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6044. Min Act: -0.0000

Data Index: 47455 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1086363 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6052. Min Act: -0.0000

Data Index: 61828 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5263. Min Act: -0.0000

Data Index: 616131 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4987. Min Act: -0.0000

Data Index: 804933 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4406. Min Act: -0.0000

Data Index: 391250 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4461. Min Act: -0.0000

Data Index: 430865 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4480. Min Act: -0.0000

Data Index: 539142 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4471. Min Act: -0.0000

Data Index: 623221 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4421. Min Act: -0.0000

Data Index: 795931 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4604. Min Act: -0.0000

Data Index: 599330 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4162. Min Act: -0.0000

Data Index: 981899 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4526. Min Act: -0.0000

Data Index: 93636 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4482. Min Act: -0.0000

Data Index: 954343 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1275637 (C4 (Web Text))

Max Activating Token Index: 57