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

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

Neuron 958 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1116. Min Range: -3.1116

Max Act: 3.1116. Min Act: -0.0000

Data Index: 277983 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.7698. Min Act: -0.0000

Data Index: 1621218 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.4961. Min Act: -0.0000

Data Index: 1500864 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.1339. Min Act: -0.0000

Data Index: 1273395 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0650. Min Act: -0.0000

Data Index: 202370 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.2084. Min Act: -0.0000

Data Index: 708105 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.9242. Min Act: -0.0000

Data Index: 1580503 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0213. Min Act: -0.0000

Data Index: 1060214 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.0951. Min Act: -0.0000

Data Index: 32105 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.8326. Min Act: -0.0000

Data Index: 1012939 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.8271. Min Act: -0.0000

Data Index: 1328312 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.9215. Min Act: -0.0000

Data Index: 773258 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.6153. Min Act: -0.0000

Data Index: 788553 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.5303. Min Act: -0.0000

Data Index: 1487854 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.6990. Min Act: -0.0000

Data Index: 327287 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.8753. Min Act: -0.0000

Data Index: 536997 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.7710. Min Act: -0.0000

Data Index: 754147 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.6401. Min Act: -0.0000

Data Index: 528544 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.6297. Min Act: -0.0000

Data Index: 602592 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 3.1116. Min Range: -3.1116

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1093202 (C4 (Web Text))

Max Activating Token Index: 112