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

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

Neuron 4252 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.7854. Min Act: -0.0001

Data Index: 59035 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.8477. Min Act: -0.0001

Data Index: 755789 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.6072. Min Act: -0.0001

Data Index: 128344 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.8080. Min Act: -0.0001

Data Index: 1415456 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.6615. Min Act: -0.0001

Data Index: 1318117 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.6469. Min Act: -0.0001

Data Index: 180560 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.4391. Min Act: -0.0001

Data Index: 1200839 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.5879. Min Act: -0.0001

Data Index: 902449 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.5000. Min Act: -0.0001

Data Index: 947987 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.4494. Min Act: -0.0001

Data Index: 889730 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.3926. Min Act: -0.0001

Data Index: 1203221 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.5385. Min Act: -0.0001

Data Index: 299581 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.5040. Min Act: -0.0001

Data Index: 803875 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.3220. Min Act: -0.0001

Data Index: 1633229 (Python Code)

Max Activating Token Index: 609

Text #14

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.4616. Min Act: -0.0001

Data Index: 1146971 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.2924. Min Act: -0.0001

Data Index: 469622 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.4268. Min Act: -0.0001

Data Index: 888254 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.2876. Min Act: -0.0001

Data Index: 928010 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.3150. Min Act: -0.0001

Data Index: 708129 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.8477. Min Range: -1.8477

Max Act: 1.3104. Min Act: -0.0001

Data Index: 1200968 (C4 (Web Text))

Max Activating Token Index: 737