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

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

Neuron 6121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1516897 (Python Code)

Max Activating Token Index: 536

Text #1

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1433583 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1387262 (Python Code)

Max Activating Token Index: 715

Text #3

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2230. Min Act: -0.0000

Data Index: 476740 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1563373 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2159. Min Act: -0.0000

Data Index: 94145 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2132. Min Act: -0.0000

Data Index: 558777 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1653106 (Python Code)

Max Activating Token Index: 612

Text #8

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1975. Min Act: -0.0000

Data Index: 711987 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1925. Min Act: -0.0000

Data Index: 395531 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1971. Min Act: -0.0000

Data Index: 482271 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1628280 (Python Code)

Max Activating Token Index: 957

Text #12

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1590195 (Python Code)

Max Activating Token Index: 512

Text #13

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1833. Min Act: -0.0000

Data Index: 99109 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1776. Min Act: -0.0000

Data Index: 868718 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1834. Min Act: -0.0000

Data Index: 690226 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1530149 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1787. Min Act: -0.0000

Data Index: 296103 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1563876 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1500350 (Python Code)

Max Activating Token Index: 288