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

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

Neuron 1049 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: 0.7524. Min Range: -0.7524

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1347620 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.7347. Min Act: -0.0000

Data Index: 249088 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.7244. Min Act: -0.0000

Data Index: 167158 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.7438. Min Act: -0.0000

Data Index: 553678 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6136. Min Act: -0.0000

Data Index: 751555 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6178. Min Act: -0.0000

Data Index: 915435 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5799. Min Act: -0.0000

Data Index: 25530 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5512. Min Act: -0.0000

Data Index: 739167 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4562. Min Act: -0.0000

Data Index: 699629 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1074269 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4853. Min Act: -0.0000

Data Index: 876977 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4532. Min Act: -0.0000

Data Index: 494863 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4428. Min Act: -0.0000

Data Index: 906485 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4469. Min Act: -0.0000

Data Index: 496546 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1003265 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4525. Min Act: -0.0000

Data Index: 924240 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4120. Min Act: -0.0000

Data Index: 339485 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1188753 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1095751 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1058797 (C4 (Web Text))

Max Activating Token Index: 880