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

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

Neuron 1201 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7585. Min Act: 0.0000

Data Index: 189821 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7069. Min Act: 0.0000

Data Index: 404843 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5826. Min Act: -0.0000

Data Index: 66340 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5104. Min Act: -0.0000

Data Index: 145389 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1421821 (Python Code)

Max Activating Token Index: 344

Text #5

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5064. Min Act: 0.0000

Data Index: 337906 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1245969 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5122. Min Act: 0.0000

Data Index: 599345 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5147. Min Act: 0.0000

Data Index: 406701 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4889. Min Act: 0.0000

Data Index: 774039 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4901. Min Act: -0.0000

Data Index: 588395 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1269562 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4852. Min Act: 0.0000

Data Index: 731108 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1558312 (Python Code)

Max Activating Token Index: 750

Text #14

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1027479 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1299059 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4575. Min Act: -0.0000

Data Index: 376176 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4482. Min Act: 0.0000

Data Index: 1051232 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1224036 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.4252. Min Act: -0.0000

Data Index: 882902 (C4 (Web Text))

Max Activating Token Index: 143