Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2552 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0662. Min Range: -1.0662

Max Act: 1.0374. Min Act: -0.0001

Data Index: 1496913 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 1.0662. Min Range: -1.0662

Max Act: 1.0662. Min Act: -0.0001

Data Index: 1520645 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 1.0662. Min Range: -1.0662

Max Act: 1.0149. Min Act: -0.0001

Data Index: 1446252 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.9487. Min Act: -0.0001

Data Index: 1619418 (Python Code)

Max Activating Token Index: 953

Text #4

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.9762. Min Act: -0.0001

Data Index: 1607570 (Python Code)

Max Activating Token Index: 639

Text #5

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8841. Min Act: -0.0001

Data Index: 1093392 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8275. Min Act: -0.0001

Data Index: 1458431 (Python Code)

Max Activating Token Index: 669

Text #7

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.9247. Min Act: -0.0001

Data Index: 1564172 (Python Code)

Max Activating Token Index: 558

Text #8

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.9414. Min Act: -0.0001

Data Index: 1115693 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.9401. Min Act: -0.0001

Data Index: 1601539 (Python Code)

Max Activating Token Index: 472

Text #10

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8425. Min Act: -0.0001

Data Index: 1516006 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8301. Min Act: -0.0001

Data Index: 1507054 (Python Code)

Max Activating Token Index: 862

Text #12

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1554281 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8209. Min Act: -0.0001

Data Index: 1578040 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8338. Min Act: -0.0001

Data Index: 1026147 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8746. Min Act: -0.0001

Data Index: 1520255 (Python Code)

Max Activating Token Index: 949

Text #16

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8726. Min Act: -0.0001

Data Index: 1443266 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8095. Min Act: -0.0001

Data Index: 1521253 (Python Code)

Max Activating Token Index: 889

Text #18

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8354. Min Act: -0.0001

Data Index: 130203 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 1.0662. Min Range: -1.0662

Max Act: 0.8114. Min Act: -0.0001

Data Index: 1391487 (Python Code)

Max Activating Token Index: 596