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

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

Neuron 3055 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: 0.5380. Min Range: -0.5380

Max Act: 0.5380. Min Act: -0.0000

Data Index: 438050 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1407916 (Python Code)

Max Activating Token Index: 361

Text #2

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4125. Min Act: -0.0000

Data Index: 932399 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1234640 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1585826 (Python Code)

Max Activating Token Index: 380

Text #5

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1593661 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1270155 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3307. Min Act: -0.0000

Data Index: 620013 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3515. Min Act: -0.0000

Data Index: 367496 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1435845 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1421073 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1127387 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1289761 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1528734 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3318. Min Act: -0.0000

Data Index: 907852 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3444. Min Act: -0.0000

Data Index: 651259 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1466815 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1225019 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1521551 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 0.5380. Min Range: -0.5380

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1309572 (C4 (Web Text))

Max Activating Token Index: 1002