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

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

Neuron 4027 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: 0.3143. Min Range: -0.3143

Max Act: 0.3143. Min Act: -0.0000

Data Index: 780833 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2230. Min Act: -0.0000

Data Index: 821909 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1326. Min Act: -0.0000

Data Index: 619482 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1083. Min Act: -0.0000

Data Index: 516587 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1543954 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1128. Min Act: -0.0000

Data Index: 541031 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1094. Min Act: -0.0000

Data Index: 560118 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1655858 (Python Code)

Max Activating Token Index: 108

Text #8

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1038. Min Act: -0.0000

Data Index: 53128 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1234. Min Act: -0.0000

Data Index: 19428 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1267249 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1133. Min Act: -0.0000

Data Index: 572005 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1572612 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1002. Min Act: -0.0000

Data Index: 636289 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1393536 (Python Code)

Max Activating Token Index: 362

Text #15

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1390189 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1065751 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1478490 (Python Code)

Max Activating Token Index: 529

Text #18

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1548011 (Python Code)

Max Activating Token Index: 354

Text #19

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1412620 (Python Code)

Max Activating Token Index: 519