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

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

Neuron 2499 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.7298. Min Act: -0.0000

Data Index: 935788 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.7309. Min Act: -0.0000

Data Index: 589479 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.7132. Min Act: -0.0000

Data Index: 514103 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6469. Min Act: -0.0000

Data Index: 465416 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.5164. Min Act: -0.0000

Data Index: 98277 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.5798. Min Act: -0.0000

Data Index: 443248 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.5770. Min Act: -0.0000

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1355390 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1459068 (Python Code)

Max Activating Token Index: 62

Text #9

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1253964 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4611. Min Act: -0.0000

Data Index: 894361 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4892. Min Act: -0.0000

Data Index: 880216 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1566557 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1028084 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4223. Min Act: -0.0000

Data Index: 321353 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1574239 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4961. Min Act: -0.0000

Data Index: 66539 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1582299 (Python Code)

Max Activating Token Index: 181

Text #18

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1615368 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.4904. Min Act: -0.0000

Data Index: 300251 (C4 (Web Text))

Max Activating Token Index: 470