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

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

Neuron 1313 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: 1.0777. Min Range: -1.0777

Max Act: 1.0777. Min Act: -0.0000

Data Index: 382896 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0689. Min Act: -0.0000

Data Index: 534709 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0586. Min Act: -0.0000

Data Index: 362300 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0519. Min Act: -0.0000

Data Index: 896037 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0601. Min Act: -0.0000

Data Index: 466946 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0072. Min Act: -0.0000

Data Index: 45361 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9777. Min Act: -0.0000

Data Index: 107511 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0011. Min Act: -0.0000

Data Index: 393085 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9605. Min Act: 0.0000

Data Index: 712715 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0206. Min Act: -0.0000

Data Index: 642295 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9270. Min Act: -0.0000

Data Index: 31848 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9557. Min Act: -0.0000

Data Index: 242925 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9802. Min Act: -0.0000

Data Index: 677461 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1280802 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9252. Min Act: 0.0000

Data Index: 123706 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9377. Min Act: 0.0000

Data Index: 426178 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9482. Min Act: 0.0000

Data Index: 599177 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.8824. Min Act: 0.0000

Data Index: 575133 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9244. Min Act: 0.0000

Data Index: 368400 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1279735 (C4 (Web Text))

Max Activating Token Index: 48