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

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

Neuron 249 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6745. Min Act: -0.0000

Data Index: 196870 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5447. Min Act: -0.0000

Data Index: 772945 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5218. Min Act: -0.0000

Data Index: 927142 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5436. Min Act: -0.0000

Data Index: 955733 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5647. Min Act: -0.0000

Data Index: 717981 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1355378 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5347. Min Act: -0.0000

Data Index: 869331 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5442. Min Act: -0.0000

Data Index: 744388 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4718. Min Act: -0.0000

Data Index: 307099 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4910. Min Act: -0.0000

Data Index: 387436 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4763. Min Act: -0.0000

Data Index: 756389 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1322031 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5034. Min Act: -0.0000

Data Index: 913448 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4572. Min Act: -0.0000

Data Index: 219439 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1267541 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4910. Min Act: -0.0000

Data Index: 225655 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4927. Min Act: -0.0000

Data Index: 233465 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1161036 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4481. Min Act: -0.0000

Data Index: 920304 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4435. Min Act: -0.0000

Data Index: 581221 (C4 (Web Text))

Max Activating Token Index: 464