Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2136 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0681. Min Act: -0.0000

Data Index: 857470 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.7073. Min Act: -0.0000

Data Index: 917663 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.7051. Min Act: -0.0000

Data Index: 93566 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1327715 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.4358. Min Act: -0.0000

Data Index: 310482 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.3257. Min Act: -0.0000

Data Index: 23081 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.3289. Min Act: -0.0000

Data Index: 1346493 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.3680. Min Act: -0.0000

Data Index: 272426 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.2637. Min Act: -0.0000

Data Index: 418446 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.1076. Min Act: -0.0000

Data Index: 616147 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.0550. Min Act: -0.0000

Data Index: 309816 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.1843. Min Act: -0.0000

Data Index: 98807 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.2341. Min Act: -0.0000

Data Index: 1024793 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.0311. Min Act: -0.0000

Data Index: 294376 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1284034 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 3.0681. Min Range: -3.0681

Max Act: 0.8911. Min Act: -0.0000

Data Index: 857929 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 3.0681. Min Range: -3.0681

Max Act: 0.9990. Min Act: -0.0000

Data Index: 160484 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 3.0681. Min Range: -3.0681

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1388873 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.0559. Min Act: -0.0000

Data Index: 278114 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 3.0681. Min Range: -3.0681

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1623342 (Python Code)

Max Activating Token Index: 949