Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 249 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5738. Min Act: -0.0001

Data Index: 982879 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5527. Min Act: -0.0001

Data Index: 714149 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5509. Min Act: -0.0001

Data Index: 863572 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5179. Min Act: -0.0001

Data Index: 184196 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4754. Min Act: -0.0001

Data Index: 1356 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4930. Min Act: -0.0001

Data Index: 950181 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4891. Min Act: -0.0001

Data Index: 5138 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1470387 (Python Code)

Max Activating Token Index: 725

Text #8

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4827. Min Act: -0.0001

Data Index: 385737 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4865. Min Act: -0.0001

Data Index: 1059087 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1162517 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4380. Min Act: -0.0001

Data Index: 443482 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4335. Min Act: -0.0001

Data Index: 613952 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4435. Min Act: -0.0001

Data Index: 57947 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4452. Min Act: -0.0001

Data Index: 237934 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4418. Min Act: -0.0001

Data Index: 562577 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4556. Min Act: -0.0001

Data Index: 529597 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4346. Min Act: -0.0001

Data Index: 806457 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.3933. Min Act: -0.0001

Data Index: 255097 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4175. Min Act: -0.0001

Data Index: 849265 (C4 (Web Text))

Max Activating Token Index: 157