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

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

Neuron 1685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.6695. Min Act: -0.0001

Data Index: 365435 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1212957 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5585. Min Act: -0.0001

Data Index: 328760 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5945. Min Act: -0.0000

Data Index: 644500 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5631. Min Act: -0.0001

Data Index: 270906 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5520. Min Act: -0.0001

Data Index: 604850 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5494. Min Act: -0.0001

Data Index: 241426 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5469. Min Act: -0.0001

Data Index: 474012 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5060. Min Act: -0.0001

Data Index: 644612 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5339. Min Act: -0.0001

Data Index: 681984 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5258. Min Act: -0.0001

Data Index: 577006 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5214. Min Act: -0.0001

Data Index: 18531 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5010. Min Act: -0.0001

Data Index: 570819 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4972. Min Act: -0.0001

Data Index: 152389 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4808. Min Act: -0.0001

Data Index: 946936 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5248. Min Act: -0.0001

Data Index: 137691 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.4928. Min Act: -0.0001

Data Index: 227706 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5047. Min Act: -0.0001

Data Index: 127973 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5197. Min Act: -0.0001

Data Index: 214923 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.6695. Min Range: -0.6695

Max Act: 0.5020. Min Act: -0.0001

Data Index: 1068885 (C4 (Web Text))

Max Activating Token Index: 823