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

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

Neuron 2518 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3065. Min Range: -2.3065

Max Act: 2.3065. Min Act: -0.0000

Data Index: 1577393 (Python Code)

Max Activating Token Index: 191

Text #1

Max Range: 2.3065. Min Range: -2.3065

Max Act: 2.2461. Min Act: -0.0000

Data Index: 1465036 (Python Code)

Max Activating Token Index: 950

Text #2

Max Range: 2.3065. Min Range: -2.3065

Max Act: 2.1799. Min Act: -0.0000

Data Index: 1535946 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 2.3065. Min Range: -2.3065

Max Act: 2.1207. Min Act: -0.0000

Data Index: 1393710 (Python Code)

Max Activating Token Index: 347

Text #4

Max Range: 2.3065. Min Range: -2.3065

Max Act: 2.0149. Min Act: -0.0000

Data Index: 1517000 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.8741. Min Act: -0.0000

Data Index: 1376972 (Python Code)

Max Activating Token Index: 309

Text #6

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.8458. Min Act: -0.0000

Data Index: 513379 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.8322. Min Act: -0.0000

Data Index: 1481664 (Python Code)

Max Activating Token Index: 470

Text #8

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.8090. Min Act: -0.0000

Data Index: 1399013 (Python Code)

Max Activating Token Index: 354

Text #9

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.8777. Min Act: -0.0000

Data Index: 293935 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.8474. Min Act: -0.0000

Data Index: 1503165 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.8244. Min Act: -0.0000

Data Index: 730274 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.7981. Min Act: -0.0000

Data Index: 640868 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.7669. Min Act: -0.0000

Data Index: 1474616 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.7424. Min Act: -0.0000

Data Index: 1595972 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.7290. Min Act: -0.0000

Data Index: 1477513 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.7175. Min Act: -0.0000

Data Index: 1064027 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.6980. Min Act: -0.0000

Data Index: 1591792 (Python Code)

Max Activating Token Index: 586

Text #18

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1311616 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 2.3065. Min Range: -2.3065

Max Act: 1.6794. Min Act: -0.0000

Data Index: 1500640 (Python Code)

Max Activating Token Index: 777