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

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

Neuron 1168 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2728. Min Act: -0.0000

Data Index: 98691 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2627. Min Act: -0.0000

Data Index: 980209 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1144875 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2257. Min Act: -0.0000

Data Index: 453716 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2494. Min Act: -0.0000

Data Index: 636462 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1165761 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2201. Min Act: -0.0000

Data Index: 263420 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2221. Min Act: -0.0000

Data Index: 323382 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2103. Min Act: -0.0000

Data Index: 485530 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2096. Min Act: -0.0000

Data Index: 153912 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2067. Min Act: -0.0000

Data Index: 291746 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1986. Min Act: -0.0000

Data Index: 384468 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2045. Min Act: -0.0000

Data Index: 324249 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1985. Min Act: -0.0000

Data Index: 619601 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2058. Min Act: -0.0000

Data Index: 575802 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1971. Min Act: -0.0000

Data Index: 148361 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1967. Min Act: -0.0000

Data Index: 968184 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1900. Min Act: -0.0000

Data Index: 750308 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.1964. Min Act: -0.0000

Data Index: 767698 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.2728. Min Range: -0.2728

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1352035 (C4 (Web Text))

Max Activating Token Index: 64