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

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

Neuron 1708 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5218. Min Range: -5.5218

Max Act: 5.3886. Min Act: -0.0001

Data Index: 283943 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 5.5218. Min Range: -5.5218

Max Act: 5.1949. Min Act: -0.0001

Data Index: 931906 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 5.5218. Min Range: -5.5218

Max Act: 5.5218. Min Act: -0.0001

Data Index: 2210 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 5.5218. Min Range: -5.5218

Max Act: 5.0881. Min Act: -0.0000

Data Index: 463863 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.8954. Min Act: -0.0001

Data Index: 54338 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.6872. Min Act: -0.0001

Data Index: 815971 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.8175. Min Act: -0.0001

Data Index: 459572 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.8860. Min Act: -0.0001

Data Index: 1261041 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.4958. Min Act: -0.0001

Data Index: 1294413 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.6008. Min Act: -0.0001

Data Index: 171115 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.5725. Min Act: -0.0001

Data Index: 1202608 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.7013. Min Act: -0.0001

Data Index: 446919 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.6598. Min Act: -0.0001

Data Index: 1299844 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.4841. Min Act: -0.0001

Data Index: 409319 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.5042. Min Act: -0.0000

Data Index: 1092438 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.4026. Min Act: -0.0001

Data Index: 913859 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.2353. Min Act: -0.0001

Data Index: 1144495 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.5718. Min Act: -0.0001

Data Index: 1039381 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.3446. Min Act: -0.0001

Data Index: 1295985 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 5.5218. Min Range: -5.5218

Max Act: 4.2908. Min Act: -0.0001

Data Index: 58821 (C4 (Web Text))

Max Activating Token Index: 456