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

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

Neuron 1520 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1552959 (Python Code)

Max Activating Token Index: 299

Text #1

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1578933 (Python Code)

Max Activating Token Index: 624

Text #2

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7081. Min Act: -0.0000

Data Index: 933477 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1334094 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7210. Min Act: -0.0000

Data Index: 444656 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1574885 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6771. Min Act: -0.0000

Data Index: 513028 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1447220 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1300680 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1184822 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1362653 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1376481 (Python Code)

Max Activating Token Index: 196

Text #12

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6487. Min Act: -0.0000

Data Index: 85028 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1537067 (Python Code)

Max Activating Token Index: 230

Text #14

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1300339 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1223305 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1541199 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1033867 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.5947. Min Act: -0.0000

Data Index: 520653 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1539810 (Python Code)

Max Activating Token Index: 905