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

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

Neuron 1084 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: 1.8283. Min Range: -1.8283

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1652749 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1386089 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4994. Min Act: -0.0000

Data Index: 850093 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1372394 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3702. Min Act: -0.0000

Data Index: 1426033 (Python Code)

Max Activating Token Index: 1001

Text #5

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.4313. Min Act: -0.0000

Data Index: 467963 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.1658. Min Act: -0.0000

Data Index: 1377761 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1640259 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1393487 (Python Code)

Max Activating Token Index: 550

Text #9

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1614280 (Python Code)

Max Activating Token Index: 839

Text #10

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1607574 (Python Code)

Max Activating Token Index: 923

Text #11

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1121792 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1449845 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.1790. Min Act: -0.0000

Data Index: 1391450 (Python Code)

Max Activating Token Index: 446

Text #14

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1646914 (Python Code)

Max Activating Token Index: 908

Text #15

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.1185. Min Act: -0.0000

Data Index: 895792 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1578521 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1514100 (Python Code)

Max Activating Token Index: 1001

Text #18

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1159083 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.8283. Min Range: -1.8283

Max Act: 1.1034. Min Act: -0.0000

Data Index: 1380967 (Python Code)

Max Activating Token Index: 860