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

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

Neuron 484 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5365. Min Range: -7.5365

Max Act: 7.5365. Min Act: -0.0000

Data Index: 1019589 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.9041. Min Act: -0.0000

Data Index: 32134 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.7116. Min Act: -0.0000

Data Index: 1100298 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.8814. Min Act: -0.0000

Data Index: 596101 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 7.5365. Min Range: -7.5365

Max Act: 7.0466. Min Act: -0.0000

Data Index: 1292168 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.4616. Min Act: -0.0000

Data Index: 633467 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.2866. Min Act: -0.0000

Data Index: 1357433 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.2849. Min Act: -0.0001

Data Index: 971190 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.2962. Min Act: -0.0001

Data Index: 1250560 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.6691. Min Act: -0.0000

Data Index: 1038269 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.0244. Min Act: -0.0000

Data Index: 147831 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.8423. Min Act: -0.0000

Data Index: 165058 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.9672. Min Act: -0.0000

Data Index: 869541 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.7459. Min Act: -0.0000

Data Index: 1147018 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.7011. Min Act: -0.0000

Data Index: 437026 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.8496. Min Act: -0.0001

Data Index: 853905 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 7.5365. Min Range: -7.5365

Max Act: 6.0451. Min Act: -0.0000

Data Index: 848061 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.8265. Min Act: -0.0000

Data Index: 576944 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.6270. Min Act: -0.0001

Data Index: 97554 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 7.5365. Min Range: -7.5365

Max Act: 5.8148. Min Act: -0.0000

Data Index: 402606 (C4 (Web Text))

Max Activating Token Index: 388