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

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

Neuron 504 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.7487. Min Act: -0.0000

Data Index: 738980 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.6719. Min Act: -0.0000

Data Index: 253901 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.7141. Min Act: -0.0000

Data Index: 691534 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.6204. Min Act: 0.0000

Data Index: 932932 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1448840 (Python Code)

Max Activating Token Index: 630

Text #5

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.6146. Min Act: 0.0000

Data Index: 27831 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.6042. Min Act: -0.0000

Data Index: 705727 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1460541 (Python Code)

Max Activating Token Index: 607

Text #8

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5373. Min Act: -0.0000

Data Index: 715446 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1507680 (Python Code)

Max Activating Token Index: 756

Text #10

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1326828 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5476. Min Act: -0.0000

Data Index: 785713 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5384. Min Act: 0.0000

Data Index: 614811 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5250. Min Act: 0.0000

Data Index: 1432380 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5208. Min Act: 0.0001

Data Index: 656227 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1376947 (Python Code)

Max Activating Token Index: 985

Text #16

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.5057. Min Act: -0.0000

Data Index: 919178 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.4898. Min Act: -0.0000

Data Index: 788464 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1503595 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.7487. Min Range: -0.7487

Max Act: 0.4935. Min Act: -0.0000

Data Index: 345320 (C4 (Web Text))

Max Activating Token Index: 330