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

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

Neuron 3832 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1010618 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2496. Min Act: -0.0001

Data Index: 1157748 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2404. Min Act: -0.0001

Data Index: 253204 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2364. Min Act: -0.0001

Data Index: 665591 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2282. Min Act: -0.0001

Data Index: 846295 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2203. Min Act: -0.0001

Data Index: 1230969 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1082544 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2131. Min Act: -0.0001

Data Index: 564814 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2051. Min Act: -0.0001

Data Index: 201649 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1263990 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1034631 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1969. Min Act: -0.0001

Data Index: 462055 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2058. Min Act: -0.0001

Data Index: 192617 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2117. Min Act: -0.0001

Data Index: 495292 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1479030 (Python Code)

Max Activating Token Index: 784

Text #15

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1792. Min Act: -0.0001

Data Index: 1005082 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1968. Min Act: -0.0001

Data Index: 788538 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1870. Min Act: -0.0001

Data Index: 999329 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1983. Min Act: -0.0001

Data Index: 812580 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1146609 (C4 (Web Text))

Max Activating Token Index: 37