Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 576 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2885. Min Act: -0.0001

Data Index: 728022 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.1918. Min Act: -0.0001

Data Index: 1243739 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.1403. Min Act: -0.0001

Data Index: 1000342 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.0452. Min Act: -0.0001

Data Index: 1215556 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.0912. Min Act: -0.0001

Data Index: 150638 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.0159. Min Act: -0.0001

Data Index: 1331687 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.0335. Min Act: -0.0001

Data Index: 1328495 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.0010. Min Act: -0.0001

Data Index: 1243074 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9768. Min Act: -0.0001

Data Index: 804679 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9344. Min Act: -0.0001

Data Index: 1225870 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1330872 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9756. Min Act: -0.0001

Data Index: 14159 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9225. Min Act: -0.0001

Data Index: 1296645 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8934. Min Act: -0.0001

Data Index: 52837 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8985. Min Act: -0.0001

Data Index: 454700 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8696. Min Act: -0.0001

Data Index: 615424 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8957. Min Act: -0.0001

Data Index: 757452 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9146. Min Act: -0.0001

Data Index: 453518 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8420. Min Act: -0.0001

Data Index: 89884 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8469. Min Act: -0.0001

Data Index: 960845 (C4 (Web Text))

Max Activating Token Index: 694