Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 139 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.7371. Min Act: -0.0001

Data Index: 918360 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.7085. Min Act: -0.0000

Data Index: 951872 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.6356. Min Act: -0.0001

Data Index: 1126552 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5804. Min Act: -0.0001

Data Index: 1272993 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5686. Min Act: -0.0001

Data Index: 936218 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5547. Min Act: -0.0001

Data Index: 22219 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5512. Min Act: -0.0000

Data Index: 345504 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5108. Min Act: -0.0001

Data Index: 780489 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4944. Min Act: -0.0001

Data Index: 820734 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5250. Min Act: -0.0001

Data Index: 1503237 (Python Code)

Max Activating Token Index: 573

Text #10

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4565. Min Act: -0.0001

Data Index: 680201 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4894. Min Act: -0.0001

Data Index: 692289 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4859. Min Act: -0.0001

Data Index: 1038811 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5037. Min Act: -0.0001

Data Index: 570997 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4957. Min Act: -0.0001

Data Index: 1214192 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5105. Min Act: -0.0001

Data Index: 844143 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4947. Min Act: -0.0001

Data Index: 852952 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5104. Min Act: -0.0001

Data Index: 568047 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5087. Min Act: -0.0000

Data Index: 101885 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4909. Min Act: -0.0001

Data Index: 470623 (C4 (Web Text))

Max Activating Token Index: 414