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

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

Neuron 185 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.4447. Min Act: -0.0001

Data Index: 1105442 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2239. Min Act: -0.0001

Data Index: 305317 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2093. Min Act: -0.0001

Data Index: 873082 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1755. Min Act: -0.0001

Data Index: 1106132 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9698. Min Act: -0.0001

Data Index: 31371 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.0016. Min Act: -0.0001

Data Index: 615993 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9971. Min Act: -0.0001

Data Index: 1055232 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.0769. Min Act: -0.0001

Data Index: 890411 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9335. Min Act: -0.0001

Data Index: 670733 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9862. Min Act: -0.0001

Data Index: 229560 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9501. Min Act: -0.0001

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8665. Min Act: -0.0001

Data Index: 776718 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8999. Min Act: -0.0001

Data Index: 741038 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8261. Min Act: -0.0001

Data Index: 576163 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9458. Min Act: -0.0001

Data Index: 957381 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8786. Min Act: -0.0001

Data Index: 224934 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9646. Min Act: -0.0001

Data Index: 1069152 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8510. Min Act: -0.0001

Data Index: 623013 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8866. Min Act: -0.0001

Data Index: 771398 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8424. Min Act: -0.0001

Data Index: 1006373 (C4 (Web Text))

Max Activating Token Index: 773