Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 708 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2715. Min Act: -0.0001

Data Index: 869565 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2517. Min Act: -0.0001

Data Index: 1497858 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2319. Min Act: -0.0001

Data Index: 276754 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1471751 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2204. Min Act: -0.0001

Data Index: 1622154 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1595455 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1972. Min Act: -0.0001

Data Index: 1619102 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2074. Min Act: -0.0001

Data Index: 583328 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2116. Min Act: -0.0001

Data Index: 170849 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1575054 (Python Code)

Max Activating Token Index: 659

Text #10

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1416781 (Python Code)

Max Activating Token Index: 554

Text #11

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1455156 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1317673 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1444117 (Python Code)

Max Activating Token Index: 991

Text #14

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1878. Min Act: -0.0001

Data Index: 1651449 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1467065 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1498227 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1443351 (Python Code)

Max Activating Token Index: 643

Text #18

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1545815 (Python Code)

Max Activating Token Index: 1008

Text #19

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.1994. Min Act: -0.0001

Data Index: 61932 (C4 (Web Text))

Max Activating Token Index: 49