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

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

Neuron 2952 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.5779. Min Act: 0.0001

Data Index: 756300 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.8287. Min Act: -0.0000

Data Index: 425339 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.4542. Min Act: -0.0000

Data Index: 721780 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.5404. Min Act: -0.0000

Data Index: 331623 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3455. Min Act: 0.0000

Data Index: 58121 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.4568. Min Act: -0.0000

Data Index: 784224 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.4365. Min Act: -0.0000

Data Index: 1128823 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3788. Min Act: -0.0000

Data Index: 712532 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.5580. Min Act: 0.0000

Data Index: 1184087 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3752. Min Act: -0.0000

Data Index: 27909 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3941. Min Act: -0.0000

Data Index: 655208 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3784. Min Act: -0.0000

Data Index: 194169 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.1067. Min Act: 0.0001

Data Index: 889503 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.2292. Min Act: -0.0000

Data Index: 1087499 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.2282. Min Act: -0.0000

Data Index: 500027 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.2259. Min Act: 0.0001

Data Index: 1121255 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.2169. Min Act: -0.0000

Data Index: 777762 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.1737. Min Act: -0.0000

Data Index: 1342005 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.0910. Min Act: 0.0001

Data Index: 270036 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.0000. Min Act: 0.0001

Data Index: 668560 (C4 (Web Text))

Max Activating Token Index: 29