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

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

Neuron 1202 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: 1.7830. Min Range: -1.7830

Max Act: 1.7830. Min Act: -0.0001

Data Index: 926496 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.5796. Min Act: -0.0001

Data Index: 1134824 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.6188. Min Act: -0.0001

Data Index: 1252333 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.5799. Min Act: -0.0001

Data Index: 530524 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4824. Min Act: -0.0001

Data Index: 1133712 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.5090. Min Act: -0.0001

Data Index: 1056099 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4990. Min Act: -0.0001

Data Index: 1319786 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1241323 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4968. Min Act: -0.0001

Data Index: 548829 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.5454. Min Act: -0.0001

Data Index: 408838 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4926. Min Act: -0.0001

Data Index: 1071534 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4725. Min Act: -0.0001

Data Index: 857574 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.5487. Min Act: -0.0001

Data Index: 722497 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.5057. Min Act: -0.0001

Data Index: 430903 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4854. Min Act: -0.0000

Data Index: 545651 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.5817. Min Act: -0.0000

Data Index: 930093 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4430. Min Act: -0.0001

Data Index: 464252 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4819. Min Act: -0.0001

Data Index: 911938 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4898. Min Act: -0.0001

Data Index: 173028 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.7830. Min Range: -1.7830

Max Act: 1.4916. Min Act: -0.0001

Data Index: 802392 (C4 (Web Text))

Max Activating Token Index: 266