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

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

Neuron 2637 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.3030. Min Act: -0.0001

Data Index: 1446270 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0656. Min Act: -0.0001

Data Index: 1638376 (Python Code)

Max Activating Token Index: 227

Text #2

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9597. Min Act: -0.0001

Data Index: 1424634 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9707. Min Act: -0.0001

Data Index: 1620318 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0013. Min Act: -0.0001

Data Index: 1475116 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9878. Min Act: -0.0001

Data Index: 1464921 (Python Code)

Max Activating Token Index: 277

Text #6

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9555. Min Act: -0.0001

Data Index: 1637871 (Python Code)

Max Activating Token Index: 522

Text #7

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0011. Min Act: -0.0001

Data Index: 1388986 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9685. Min Act: -0.0001

Data Index: 1450562 (Python Code)

Max Activating Token Index: 943

Text #9

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9543. Min Act: -0.0001

Data Index: 1549066 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9296. Min Act: -0.0001

Data Index: 1583348 (Python Code)

Max Activating Token Index: 196

Text #11

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9807. Min Act: -0.0001

Data Index: 1622076 (Python Code)

Max Activating Token Index: 849

Text #12

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9580. Min Act: -0.0001

Data Index: 1535338 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8995. Min Act: -0.0001

Data Index: 1641954 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8921. Min Act: -0.0001

Data Index: 1445900 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9177. Min Act: -0.0001

Data Index: 1632507 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1653381 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9496. Min Act: -0.0001

Data Index: 1409227 (Python Code)

Max Activating Token Index: 286

Text #18

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9155. Min Act: -0.0001

Data Index: 1580853 (Python Code)

Max Activating Token Index: 43

Text #19

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8889. Min Act: -0.0001

Data Index: 1507425 (Python Code)

Max Activating Token Index: 189