Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2679 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.3404. Min Act: -0.0001

Data Index: 1529334 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1598800 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1592131 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1427312 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1639437 (Python Code)

Max Activating Token Index: 648

Text #5

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1393388 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1404219 (Python Code)

Max Activating Token Index: 502

Text #7

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1450335 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1556667 (Python Code)

Max Activating Token Index: 239

Text #9

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1400056 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1529779 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1441019 (Python Code)

Max Activating Token Index: 313

Text #12

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1478304 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1464578 (Python Code)

Max Activating Token Index: 878

Text #14

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1492767 (Python Code)

Max Activating Token Index: 372

Text #15

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1649593 (Python Code)

Max Activating Token Index: 419

Text #16

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1400339 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1405319 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9064. Min Act: -0.0000

Data Index: 347516 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1504927 (Python Code)

Max Activating Token Index: 407