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

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

Neuron 5289 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9639. Min Act: -0.0001

Data Index: 1276240 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9526. Min Act: -0.0001

Data Index: 59774 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.7692. Min Act: -0.0001

Data Index: 1073438 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.7449. Min Act: -0.0001

Data Index: 111414 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6668. Min Act: -0.0001

Data Index: 371956 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6503. Min Act: -0.0001

Data Index: 1252995 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6198. Min Act: -0.0001

Data Index: 30887 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6155. Min Act: -0.0001

Data Index: 365312 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6223. Min Act: -0.0001

Data Index: 496242 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6111. Min Act: -0.0001

Data Index: 1575457 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6180. Min Act: -0.0001

Data Index: 987536 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6213. Min Act: -0.0001

Data Index: 312201 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6086. Min Act: -0.0001

Data Index: 1018013 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6034. Min Act: -0.0001

Data Index: 688425 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.5938. Min Act: -0.0001

Data Index: 477668 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.5944. Min Act: -0.0001

Data Index: 1570079 (Python Code)

Max Activating Token Index: 821

Text #16

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.5947. Min Act: -0.0001

Data Index: 304919 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.5923. Min Act: -0.0001

Data Index: 145784 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.6011. Min Act: -0.0001

Data Index: 476829 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.5990. Min Act: -0.0001

Data Index: 1330410 (C4 (Web Text))

Max Activating Token Index: 654