Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1951 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0000

Data Index: 591920 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1098982 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1095023 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9755. Min Act: -0.0000

Data Index: 282419 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9397. Min Act: -0.0000

Data Index: 917001 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1237891 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9399. Min Act: -0.0000

Data Index: 97417 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9308. Min Act: -0.0000

Data Index: 838664 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1356064 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8709. Min Act: -0.0000

Data Index: 448556 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8310. Min Act: -0.0000

Data Index: 751899 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8364. Min Act: -0.0000

Data Index: 891658 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7956. Min Act: -0.0000

Data Index: 67241 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1357160 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1211240 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7278. Min Act: -0.0000

Data Index: 527697 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8245. Min Act: -0.0000

Data Index: 174098 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8254. Min Act: -0.0000

Data Index: 952470 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1260603 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1188557 (C4 (Web Text))

Max Activating Token Index: 784