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

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

Neuron 3929 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1359271 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.6650. Min Act: -0.0000

Data Index: 989431 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.6737. Min Act: -0.0000

Data Index: 860667 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.6738. Min Act: -0.0000

Data Index: 883599 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5875. Min Act: -0.0000

Data Index: 879351 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.6316. Min Act: -0.0000

Data Index: 157613 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.6031. Min Act: 0.0000

Data Index: 1186969 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.6775. Min Act: -0.0000

Data Index: 827164 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5938. Min Act: 0.0000

Data Index: 553702 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5699. Min Act: 0.0000

Data Index: 1165486 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5422. Min Act: -0.0000

Data Index: 123086 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5247. Min Act: -0.0000

Data Index: 814591 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5584. Min Act: -0.0000

Data Index: 669885 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5491. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5195. Min Act: -0.0000

Data Index: 246192 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5008. Min Act: -0.0000

Data Index: 672572 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.4870. Min Act: -0.0000

Data Index: 904315 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1218966 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1230567 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.8062. Min Range: -0.8062

Max Act: 0.5130. Min Act: -0.0000

Data Index: 660411 (C4 (Web Text))

Max Activating Token Index: 563