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

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

Neuron 2139 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: 3.0933. Min Range: -3.0933

Max Act: 3.0933. Min Act: -0.0000

Data Index: 1032588 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.4562. Min Act: -0.0000

Data Index: 396393 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.6984. Min Act: -0.0001

Data Index: 587582 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.2597. Min Act: -0.0001

Data Index: 636369 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.2535. Min Act: -0.0000

Data Index: 465045 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.2075. Min Act: -0.0001

Data Index: 1116318 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.2068. Min Act: -0.0001

Data Index: 578736 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.1112. Min Act: -0.0001

Data Index: 1275064 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.4662. Min Act: -0.0001

Data Index: 1074544 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 3.0933. Min Range: -3.0933

Max Act: 1.7761. Min Act: -0.0001

Data Index: 778308 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.1196. Min Act: -0.0001

Data Index: 609434 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.0096. Min Act: -0.0001

Data Index: 1148247 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 3.0933. Min Range: -3.0933

Max Act: 1.8958. Min Act: -0.0000

Data Index: 285066 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.1107. Min Act: -0.0001

Data Index: 1526295 (Python Code)

Max Activating Token Index: 573

Text #14

Max Range: 3.0933. Min Range: -3.0933

Max Act: 1.8852. Min Act: -0.0001

Data Index: 1003012 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 3.0933. Min Range: -3.0933

Max Act: 1.8683. Min Act: -0.0001

Data Index: 1355416 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 3.0933. Min Range: -3.0933

Max Act: 1.9395. Min Act: -0.0001

Data Index: 566949 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 3.0933. Min Range: -3.0933

Max Act: 1.8093. Min Act: -0.0001

Data Index: 873885 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 3.0933. Min Range: -3.0933

Max Act: 1.6841. Min Act: -0.0001

Data Index: 1072449 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 3.0933. Min Range: -3.0933

Max Act: 2.2197. Min Act: -0.0001

Data Index: 730334 (C4 (Web Text))

Max Activating Token Index: 309