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

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

Neuron 5860 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: 1.6116. Min Range: -1.6116

Max Act: 1.6116. Min Act: -0.0000

Data Index: 64505 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.4414. Min Act: -0.0000

Data Index: 864340 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.4267. Min Act: -0.0000

Data Index: 959526 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.3098. Min Act: -0.0000

Data Index: 725964 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.3840. Min Act: -0.0000

Data Index: 770495 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.2009. Min Act: -0.0000

Data Index: 117504 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.2875. Min Act: -0.0000

Data Index: 672062 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1278628 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1314144 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.2496. Min Act: 0.0000

Data Index: 584509 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.1727. Min Act: -0.0000

Data Index: 940216 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.1491. Min Act: -0.0000

Data Index: 628804 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.2090. Min Act: -0.0000

Data Index: 719946 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.1279. Min Act: -0.0000

Data Index: 74653 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1101859 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.0610. Min Act: -0.0000

Data Index: 359048 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1018067 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 1.6116. Min Range: -1.6116

Max Act: 0.9897. Min Act: -0.0000

Data Index: 757028 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.6116. Min Range: -1.6116

Max Act: 1.1059. Min Act: -0.0000

Data Index: 698052 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.6116. Min Range: -1.6116

Max Act: 0.9909. Min Act: -0.0000

Data Index: 754009 (C4 (Web Text))

Max Activating Token Index: 168