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

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

Neuron 1058 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: 3.3614. Min Range: -3.3614

Max Act: 3.3614. Min Act: -0.0000

Data Index: 364925 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.9555. Min Act: -0.0000

Data Index: 402406 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.7223. Min Act: -0.0000

Data Index: 1171626 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.6635. Min Act: -0.0000

Data Index: 1427383 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.4817. Min Act: -0.0000

Data Index: 1607741 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.3279. Min Act: -0.0000

Data Index: 768184 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.2611. Min Act: -0.0000

Data Index: 585084 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.1069. Min Act: -0.0000

Data Index: 1345258 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.2351. Min Act: -0.0000

Data Index: 816348 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.9750. Min Act: -0.0000

Data Index: 537369 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.9507. Min Act: -0.0000

Data Index: 44624 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.0433. Min Act: -0.0000

Data Index: 18288 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 3.3614. Min Range: -3.3614

Max Act: 2.0259. Min Act: -0.0000

Data Index: 1390756 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.9441. Min Act: -0.0000

Data Index: 27069 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.9497. Min Act: -0.0000

Data Index: 1232213 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.9482. Min Act: -0.0000

Data Index: 1060848 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.7220. Min Act: -0.0000

Data Index: 821945 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1373729 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.9147. Min Act: -0.0000

Data Index: 1271815 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.3614. Min Range: -3.3614

Max Act: 1.8865. Min Act: -0.0000

Data Index: 500008 (C4 (Web Text))

Max Activating Token Index: 825