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

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

Neuron 181 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4683. Min Range: -3.4683

Max Act: 3.4683. Min Act: -0.0000

Data Index: 1174392 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.9443. Min Act: -0.0000

Data Index: 400447 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 3.4683. Min Range: -3.4683

Max Act: 3.0832. Min Act: -0.0000

Data Index: 932188 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.7984. Min Act: -0.0000

Data Index: 601478 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.8869. Min Act: -0.0000

Data Index: 1098604 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.8716. Min Act: -0.0000

Data Index: 253011 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.8067. Min Act: -0.0000

Data Index: 464340 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.6312. Min Act: -0.0000

Data Index: 580681 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.8319. Min Act: -0.0000

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.4099. Min Act: -0.0000

Data Index: 988721 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.6312. Min Act: -0.0000

Data Index: 31320 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.6315. Min Act: -0.0000

Data Index: 639235 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.6519. Min Act: -0.0000

Data Index: 1270528 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.6489. Min Act: -0.0000

Data Index: 1262557 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.4909. Min Act: -0.0000

Data Index: 979895 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.3623. Min Act: -0.0000

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.4959. Min Act: -0.0000

Data Index: 1175434 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.4969. Min Act: -0.0000

Data Index: 1346303 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.4520. Min Act: -0.0000

Data Index: 1268836 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 3.4683. Min Range: -3.4683

Max Act: 2.4526. Min Act: -0.0000

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 883