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

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

Neuron 3475 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: 1.4062. Min Range: -1.4062

Max Act: 1.4062. Min Act: -0.0000

Data Index: 1246880 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.3285. Min Act: -0.0000

Data Index: 484695 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1057917 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.2064. Min Act: -0.0000

Data Index: 439079 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.2312. Min Act: -0.0000

Data Index: 679316 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.1932. Min Act: -0.0000

Data Index: 202968 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.2268. Min Act: -0.0000

Data Index: 161389 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.2153. Min Act: -0.0000

Data Index: 801395 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.1948. Min Act: -0.0000

Data Index: 40615 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.1188. Min Act: -0.0000

Data Index: 905415 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1105317 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.1013. Min Act: -0.0000

Data Index: 421136 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.0853. Min Act: -0.0000

Data Index: 879737 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.0948. Min Act: -0.0000

Data Index: 855565 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1228442 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.0785. Min Act: -0.0000

Data Index: 574017 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.0636. Min Act: -0.0000

Data Index: 933152 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.0495. Min Act: -0.0000

Data Index: 10081 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.0532. Min Act: -0.0000

Data Index: 804479 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 1.4062. Min Range: -1.4062

Max Act: 1.0476. Min Act: -0.0000

Data Index: 397921 (C4 (Web Text))

Max Activating Token Index: 150