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

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

Neuron 3734 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.9299. Min Act: 0.0001

Data Index: 805721 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7501. Min Act: 0.0000

Data Index: 581036 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7649. Min Act: -0.0000

Data Index: 878781 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7070. Min Act: -0.0000

Data Index: 814978 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1000132 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7027. Min Act: -0.0000

Data Index: 416221 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1260121 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6210. Min Act: -0.0000

Data Index: 834981 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6010. Min Act: -0.0000

Data Index: 437884 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1283990 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5706. Min Act: -0.0000

Data Index: 558070 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5914. Min Act: 0.0001

Data Index: 892046 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5722. Min Act: -0.0000

Data Index: 821177 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5525. Min Act: -0.0000

Data Index: 462178 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5609. Min Act: 0.0001

Data Index: 513682 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1215987 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5508. Min Act: -0.0000

Data Index: 471496 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5496. Min Act: 0.0001

Data Index: 472732 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1296366 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1116752 (C4 (Web Text))

Max Activating Token Index: 777