Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4173 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.9775. Min Act: -0.0001

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.9673. Min Act: -0.0001

Data Index: 906357 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.9523. Min Act: -0.0001

Data Index: 1114099 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.9622. Min Act: -0.0001

Data Index: 423607 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.9445. Min Act: -0.0001

Data Index: 44328 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.9438. Min Act: -0.0001

Data Index: 1108855 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.9144. Min Act: -0.0001

Data Index: 102247 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.8077. Min Act: -0.0001

Data Index: 729514 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.8037. Min Act: -0.0001

Data Index: 677430 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.8259. Min Act: -0.0001

Data Index: 523678 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.7461. Min Act: -0.0001

Data Index: 441696 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.7605. Min Act: -0.0001

Data Index: 847564 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.8292. Min Act: -0.0001

Data Index: 668581 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.7841. Min Act: -0.0001

Data Index: 902361 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.8279. Min Act: -0.0002

Data Index: 221906 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.8175. Min Act: -0.0002

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.8501. Min Act: -0.0001

Data Index: 730548 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.7325. Min Act: -0.0002

Data Index: 531943 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.7861. Min Act: -0.0001

Data Index: 992690 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.9775. Min Range: -0.9775

Max Act: 0.7490. Min Act: -0.0001

Data Index: 396599 (C4 (Web Text))

Max Activating Token Index: 724