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

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

Neuron 5699 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5497. Min Act: -0.0000

Data Index: 282240 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5125. Min Act: -0.0000

Data Index: 632074 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4899. Min Act: -0.0000

Data Index: 396761 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4380. Min Act: -0.0000

Data Index: 629706 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4214. Min Act: -0.0001

Data Index: 1087995 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4261. Min Act: -0.0000

Data Index: 497195 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1477337 (Python Code)

Max Activating Token Index: 476

Text #7

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1326376 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1488312 (Python Code)

Max Activating Token Index: 342

Text #9

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3710. Min Act: -0.0000

Data Index: 30476 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3835. Min Act: -0.0000

Data Index: 62743 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3922. Min Act: -0.0000

Data Index: 44310 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3768. Min Act: -0.0000

Data Index: 46738 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1500158 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3633. Min Act: -0.0000

Data Index: 336874 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4164. Min Act: -0.0000

Data Index: 191128 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3397. Min Act: -0.0001

Data Index: 1211103 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3582. Min Act: -0.0001

Data Index: 541610 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1025813 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3427. Min Act: -0.0000

Data Index: 254425 (C4 (Web Text))

Max Activating Token Index: 878