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

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

Neuron 564 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: 2.3510. Min Range: -2.3510

Max Act: 2.1573. Min Act: -0.0000

Data Index: 341439 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 2.3510. Min Range: -2.3510

Max Act: 2.3510. Min Act: -0.0001

Data Index: 1106976 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 2.3510. Min Range: -2.3510

Max Act: 2.2664. Min Act: -0.0000

Data Index: 805759 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.9851. Min Act: -0.0000

Data Index: 1504515 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 2.3510. Min Range: -2.3510

Max Act: 2.0271. Min Act: -0.0001

Data Index: 1240566 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1483353 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.9670. Min Act: -0.0000

Data Index: 906181 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.8803. Min Act: -0.0001

Data Index: 1492141 (Python Code)

Max Activating Token Index: 160

Text #8

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.9601. Min Act: -0.0001

Data Index: 827526 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.9428. Min Act: -0.0001

Data Index: 569350 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.9292. Min Act: -0.0000

Data Index: 1000221 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 2.3510. Min Range: -2.3510

Max Act: 2.0254. Min Act: -0.0001

Data Index: 178691 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 2.3510. Min Range: -2.3510

Max Act: 2.0034. Min Act: -0.0001

Data Index: 1558770 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.6012. Min Act: -0.0000

Data Index: 1495482 (Python Code)

Max Activating Token Index: 225

Text #14

Max Range: 2.3510. Min Range: -2.3510

Max Act: 2.0049. Min Act: -0.0001

Data Index: 370516 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.8750. Min Act: -0.0000

Data Index: 935082 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1519503 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.8017. Min Act: -0.0000

Data Index: 1560358 (Python Code)

Max Activating Token Index: 926

Text #18

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.8114. Min Act: -0.0001

Data Index: 879556 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 2.3510. Min Range: -2.3510

Max Act: 1.6909. Min Act: -0.0000

Data Index: 1436247 (Python Code)

Max Activating Token Index: 677