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

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

Neuron 4443 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0707. Min Range: -3.0707

Max Act: 3.0707. Min Act: -0.0000

Data Index: 657626 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.6715. Min Act: -0.0000

Data Index: 181433 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.5465. Min Act: -0.0000

Data Index: 871090 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.4993. Min Act: -0.0000

Data Index: 293175 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.2404. Min Act: -0.0000

Data Index: 760742 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.3173. Min Act: -0.0000

Data Index: 957958 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.9652. Min Act: -0.0000

Data Index: 812683 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.0839. Min Act: -0.0000

Data Index: 496009 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.2850. Min Act: -0.0000

Data Index: 1247378 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.0694. Min Act: -0.0000

Data Index: 999287 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.9656. Min Act: -0.0000

Data Index: 1026084 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.8120. Min Act: -0.0000

Data Index: 1013023 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.9597. Min Act: -0.0000

Data Index: 697997 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.1347. Min Act: -0.0000

Data Index: 927517 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.8532. Min Act: -0.0000

Data Index: 1018550 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 3.0707. Min Range: -3.0707

Max Act: 2.0833. Min Act: -0.0000

Data Index: 633299 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.9753. Min Act: -0.0000

Data Index: 783358 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.9157. Min Act: -0.0000

Data Index: 64858 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.9649. Min Act: -0.0000

Data Index: 676521 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.0707. Min Range: -3.0707

Max Act: 1.9310. Min Act: -0.0000

Data Index: 327936 (C4 (Web Text))

Max Activating Token Index: 708