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

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

Neuron 2896 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: 1.1782. Min Range: -1.1782

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1373917 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9898. Min Act: -0.0000

Data Index: 501101 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1432345 (Python Code)

Max Activating Token Index: 989

Text #3

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1615264 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1063365 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8368. Min Act: -0.0000

Data Index: 189238 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1497216 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8031. Min Act: -0.0000

Data Index: 626270 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8024. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1379580 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6763. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6992. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1618689 (Python Code)

Max Activating Token Index: 534

Text #13

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1420099 (Python Code)

Max Activating Token Index: 549

Text #14

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.4915. Min Act: -0.0000

Data Index: 640470 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1363216 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1446813 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1383163 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6703. Min Act: -0.0000

Data Index: 917704 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1549148 (Python Code)

Max Activating Token Index: 775