Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3676 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1284438 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1418. Min Act: -0.0000

Data Index: 617924 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.2075. Min Act: -0.0000

Data Index: 1003679 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1568677 (Python Code)

Max Activating Token Index: 457

Text #4

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1411. Min Act: -0.0000

Data Index: 565408 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1186. Min Act: -0.0000

Data Index: 300606 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1663. Min Act: -0.0000

Data Index: 551570 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1129. Min Act: -0.0000

Data Index: 218950 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1136488 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1469. Min Act: -0.0000

Data Index: 210438 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1524299 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1235203 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0615. Min Act: -0.0000

Data Index: 1247619 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1226799 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0411. Min Act: -0.0000

Data Index: 746033 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1597959 (Python Code)

Max Activating Token Index: 962

Text #16

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9677. Min Act: -0.0000

Data Index: 772700 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9638. Min Act: -0.0000

Data Index: 220876 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0318. Min Act: -0.0000

Data Index: 710199 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0676. Min Act: -0.0000

Data Index: 393051 (C4 (Web Text))

Max Activating Token Index: 274