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

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

Neuron 2513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.4613. Min Act: -0.0000

Data Index: 708424 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.4513. Min Act: -0.0000

Data Index: 211948 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1204444 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3935. Min Act: -0.0000

Data Index: 840583 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1579042 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3770. Min Act: -0.0000

Data Index: 579918 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3729. Min Act: -0.0000

Data Index: 192690 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3549. Min Act: -0.0000

Data Index: 570745 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3450. Min Act: -0.0000

Data Index: 744160 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3432. Min Act: -0.0000

Data Index: 369625 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1254824 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1255221 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3520. Min Act: -0.0000

Data Index: 492088 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3458. Min Act: -0.0000

Data Index: 148149 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1056334 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3423. Min Act: -0.0000

Data Index: 47536 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3271. Min Act: -0.0000

Data Index: 339270 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3136. Min Act: -0.0000

Data Index: 923869 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3215. Min Act: -0.0000

Data Index: 609606 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.4613. Min Range: -0.4613

Max Act: 0.3185. Min Act: -0.0000

Data Index: 460375 (C4 (Web Text))

Max Activating Token Index: 474