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

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

Neuron 2189 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.6071. Min Act: -0.0000

Data Index: 1407075 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.4584. Min Act: -0.0000

Data Index: 486205 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1389467 (Python Code)

Max Activating Token Index: 612

Text #3

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1421963 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2697. Min Act: -0.0000

Data Index: 199670 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1001678 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1483925 (Python Code)

Max Activating Token Index: 398

Text #7

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1588969 (Python Code)

Max Activating Token Index: 141

Text #8

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1504723 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1580947 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1406870 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.3357. Min Act: -0.0000

Data Index: 500620 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1572275 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2359. Min Act: -0.0000

Data Index: 854835 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1544757 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2184. Min Act: -0.0000

Data Index: 999501 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1560274 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2856. Min Act: -0.0000

Data Index: 62211 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2065. Min Act: 0.0000

Data Index: 141589 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.6071. Min Range: -1.6071

Max Act: 1.2384. Min Act: -0.0000

Data Index: 64973 (C4 (Web Text))

Max Activating Token Index: 632