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

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

Neuron 95 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.2773. Min Act: -0.0001

Data Index: 713456 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0778. Min Act: -0.0001

Data Index: 944878 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0743. Min Act: -0.0001

Data Index: 711883 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1369. Min Act: -0.0000

Data Index: 810560 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0288. Min Act: -0.0001

Data Index: 1016755 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1018. Min Act: -0.0001

Data Index: 1324952 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0152. Min Act: -0.0001

Data Index: 644743 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0056. Min Act: -0.0001

Data Index: 1048748 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9562. Min Act: -0.0001

Data Index: 469835 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1322245 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9793. Min Act: -0.0001

Data Index: 569300 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1065402 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9570. Min Act: -0.0000

Data Index: 229834 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9533. Min Act: -0.0001

Data Index: 387591 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9730. Min Act: -0.0001

Data Index: 218219 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0013. Min Act: -0.0000

Data Index: 894817 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9375. Min Act: -0.0000

Data Index: 702929 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1102671 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1133572 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9100. Min Act: -0.0001

Data Index: 1208839 (C4 (Web Text))

Max Activating Token Index: 22