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

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

Neuron 3054 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7309. Min Act: -0.0001

Data Index: 541509 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7709. Min Act: -0.0001

Data Index: 1117171 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7220. Min Act: -0.0001

Data Index: 792839 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.7271. Min Act: -0.0001

Data Index: 619166 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6328. Min Act: -0.0001

Data Index: 32477 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6106. Min Act: -0.0001

Data Index: 949400 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6404. Min Act: -0.0001

Data Index: 567301 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.6006. Min Act: -0.0001

Data Index: 539176 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5649. Min Act: -0.0001

Data Index: 505297 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5754. Min Act: -0.0001

Data Index: 726233 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5203. Min Act: -0.0001

Data Index: 1259351 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5304. Min Act: -0.0001

Data Index: 459820 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5927. Min Act: -0.0001

Data Index: 953755 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5254. Min Act: -0.0001

Data Index: 337949 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5058. Min Act: -0.0001

Data Index: 461337 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5089. Min Act: -0.0001

Data Index: 173982 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5179. Min Act: -0.0001

Data Index: 670201 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5137. Min Act: -0.0001

Data Index: 931310 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.4764. Min Act: -0.0001

Data Index: 231584 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.7709. Min Range: -0.7709

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1109666 (C4 (Web Text))

Max Activating Token Index: 915