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

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

Neuron 2467 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: 2.4600. Min Range: -2.4600

Max Act: 2.1800. Min Act: -0.0000

Data Index: 505271 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.4600. Min Act: -0.0000

Data Index: 1072738 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.3120. Min Act: -0.0000

Data Index: 74167 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.1056. Min Act: -0.0000

Data Index: 450022 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.3038. Min Act: -0.0000

Data Index: 1307233 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0979. Min Act: -0.0000

Data Index: 937413 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.2218. Min Act: -0.0000

Data Index: 198820 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0803. Min Act: -0.0000

Data Index: 905473 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.9430. Min Act: -0.0000

Data Index: 560379 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0316. Min Act: -0.0000

Data Index: 1068434 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0178. Min Act: -0.0000

Data Index: 66298 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.9925. Min Act: -0.0000

Data Index: 1149158 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.9653. Min Act: -0.0000

Data Index: 704920 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0281. Min Act: -0.0000

Data Index: 1338504 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.1394. Min Act: -0.0000

Data Index: 921562 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.9163. Min Act: -0.0000

Data Index: 931773 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.9201. Min Act: -0.0000

Data Index: 142049 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0374. Min Act: -0.0000

Data Index: 1286873 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.6094. Min Act: -0.0000

Data Index: 577292 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.9542. Min Act: -0.0000

Data Index: 981355 (C4 (Web Text))

Max Activating Token Index: 224