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

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

Neuron 4947 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.6331. Min Act: -0.0000

Data Index: 1133724 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.3059. Min Act: -0.0000

Data Index: 308532 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.4474. Min Act: -0.0000

Data Index: 110435 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.2715. Min Act: -0.0000

Data Index: 296884 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.0464. Min Act: -0.0000

Data Index: 727214 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.2511. Min Act: -0.0000

Data Index: 9706 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.1318. Min Act: -0.0000

Data Index: 278649 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.2586. Min Act: -0.0000

Data Index: 796039 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.1979. Min Act: -0.0000

Data Index: 446275 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.1954. Min Act: -0.0000

Data Index: 66713 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.2824. Min Act: -0.0000

Data Index: 816307 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.1530. Min Act: -0.0000

Data Index: 245936 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.2400. Min Act: -0.0000

Data Index: 779198 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.1329. Min Act: -0.0000

Data Index: 1286086 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.0008. Min Act: -0.0000

Data Index: 1298839 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 2.6331. Min Range: -2.6331

Max Act: 1.9821. Min Act: -0.0000

Data Index: 967200 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 2.6331. Min Range: -2.6331

Max Act: 1.9813. Min Act: -0.0000

Data Index: 629905 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 2.6331. Min Range: -2.6331

Max Act: 1.9715. Min Act: -0.0000

Data Index: 753618 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 2.6331. Min Range: -2.6331

Max Act: 1.9575. Min Act: -0.0000

Data Index: 138122 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 2.6331. Min Range: -2.6331

Max Act: 2.0552. Min Act: -0.0000

Data Index: 416481 (C4 (Web Text))

Max Activating Token Index: 105