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

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

Neuron 1159 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.1544. Min Range: -10.1544

Max Act: 10.1544. Min Act: -0.0000

Data Index: 922946 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 10.1544. Min Range: -10.1544

Max Act: 9.9268. Min Act: -0.0000

Data Index: 720920 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 10.1544. Min Range: -10.1544

Max Act: 10.0721. Min Act: -0.0000

Data Index: 1017111 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 10.1544. Min Range: -10.1544

Max Act: 10.0650. Min Act: -0.0000

Data Index: 558625 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 10.1544. Min Range: -10.1544

Max Act: 9.6746. Min Act: -0.0000

Data Index: 48291 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 10.1544. Min Range: -10.1544

Max Act: 9.4254. Min Act: -0.0000

Data Index: 1251197 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 10.1544. Min Range: -10.1544

Max Act: 9.4070. Min Act: -0.0000

Data Index: 480622 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 10.1544. Min Range: -10.1544

Max Act: 9.4060. Min Act: -0.0000

Data Index: 37526 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.8276. Min Act: -0.0000

Data Index: 671195 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 10.1544. Min Range: -10.1544

Max Act: 9.4928. Min Act: -0.0000

Data Index: 443601 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 10.1544. Min Range: -10.1544

Max Act: 9.1853. Min Act: -0.0000

Data Index: 893205 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.9294. Min Act: -0.0000

Data Index: 765512 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.7382. Min Act: -0.0000

Data Index: 656137 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.4662. Min Act: -0.0000

Data Index: 1099708 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.4520. Min Act: -0.0000

Data Index: 584437 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.4037. Min Act: -0.0000

Data Index: 1197103 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.4004. Min Act: -0.0000

Data Index: 1111568 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.3786. Min Act: -0.0000

Data Index: 1299534 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.3595. Min Act: -0.0000

Data Index: 1088057 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 10.1544. Min Range: -10.1544

Max Act: 8.0027. Min Act: -0.0000

Data Index: 503298 (C4 (Web Text))

Max Activating Token Index: 969