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

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

Neuron 4017 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.8924. Min Act: -0.0000

Data Index: 1305136 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.7001. Min Act: -0.0000

Data Index: 460566 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.6848. Min Act: -0.0000

Data Index: 1277604 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.6851. Min Act: -0.0000

Data Index: 244951 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.7647. Min Act: -0.0000

Data Index: 820191 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.5508. Min Act: -0.0000

Data Index: 1191694 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.4292. Min Act: -0.0000

Data Index: 77930 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.4607. Min Act: -0.0000

Data Index: 471969 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1137680 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3503. Min Act: -0.0000

Data Index: 1290607 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3572. Min Act: -0.0000

Data Index: 818725 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.4137. Min Act: -0.0000

Data Index: 950978 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.2260. Min Act: -0.0000

Data Index: 14560 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1192718 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3659. Min Act: -0.0000

Data Index: 379403 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3555. Min Act: -0.0001

Data Index: 90891 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.2827. Min Act: -0.0000

Data Index: 178532 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.3130. Min Act: -0.0001

Data Index: 490934 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.4010. Min Act: -0.0000

Data Index: 427612 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.8924. Min Range: -1.8924

Max Act: 1.1596. Min Act: -0.0000

Data Index: 252782 (C4 (Web Text))

Max Activating Token Index: 775