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

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

Neuron 1433 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.3084. Min Act: -0.0000

Data Index: 578980 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2444. Min Act: -0.0000

Data Index: 626138 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2226. Min Act: -0.0000

Data Index: 498083 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2043. Min Act: -0.0000

Data Index: 801540 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2000. Min Act: -0.0000

Data Index: 931295 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1393537 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1260396 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1956. Min Act: -0.0000

Data Index: 560443 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1950. Min Act: -0.0000

Data Index: 677455 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2013. Min Act: -0.0000

Data Index: 753316 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1270383 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1915. Min Act: -0.0000

Data Index: 144740 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1893. Min Act: -0.0000

Data Index: 771824 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1951. Min Act: -0.0000

Data Index: 795472 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1884. Min Act: -0.0000

Data Index: 214275 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1466666 (Python Code)

Max Activating Token Index: 377

Text #16

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1853. Min Act: -0.0000

Data Index: 830036 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1732. Min Act: -0.0000

Data Index: 879044 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1220314 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1839. Min Act: -0.0000

Data Index: 926736 (C4 (Web Text))

Max Activating Token Index: 803