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

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

Neuron 3898 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0772. Min Range: -4.0772

Max Act: 4.0772. Min Act: 0.0000

Data Index: 38080 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 4.0772. Min Range: -4.0772

Max Act: 3.6942. Min Act: -0.0000

Data Index: 197354 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.7683. Min Act: -0.0000

Data Index: 1159067 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.4319. Min Act: -0.0000

Data Index: 666175 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.6598. Min Act: -0.0000

Data Index: 497167 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.7313. Min Act: -0.0000

Data Index: 1655579 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.7005. Min Act: -0.0000

Data Index: 1147003 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.1036. Min Act: -0.0000

Data Index: 305540 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.2185. Min Act: 0.0000

Data Index: 328063 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.2575. Min Act: -0.0000

Data Index: 549785 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.4037. Min Act: -0.0000

Data Index: 1263626 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.1486. Min Act: -0.0000

Data Index: 1464998 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.0289. Min Act: -0.0000

Data Index: 838249 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.0119. Min Act: -0.0000

Data Index: 752988 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 4.0772. Min Range: -4.0772

Max Act: 1.8778. Min Act: -0.0000

Data Index: 1562990 (Python Code)

Max Activating Token Index: 545

Text #15

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.1055. Min Act: 0.0000

Data Index: 535723 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.0886. Min Act: -0.0000

Data Index: 565491 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 4.0772. Min Range: -4.0772

Max Act: 1.9997. Min Act: -0.0000

Data Index: 157713 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.2778. Min Act: -0.0000

Data Index: 700749 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 4.0772. Min Range: -4.0772

Max Act: 2.1684. Min Act: -0.0000

Data Index: 127277 (C4 (Web Text))

Max Activating Token Index: 960