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

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

Neuron 2245 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7893. Min Act: -0.0001

Data Index: 472395 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7220. Min Act: -0.0001

Data Index: 1494245 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7926. Min Act: -0.0001

Data Index: 530837 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.8050. Min Act: -0.0001

Data Index: 271293 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7768. Min Act: -0.0001

Data Index: 457936 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7656. Min Act: -0.0001

Data Index: 738538 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7105. Min Act: -0.0001

Data Index: 729350 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7078. Min Act: -0.0001

Data Index: 844207 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.6985. Min Act: -0.0001

Data Index: 686770 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7413. Min Act: -0.0001

Data Index: 154228 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7592. Min Act: -0.0001

Data Index: 653134 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.7077. Min Act: -0.0001

Data Index: 460055 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.6871. Min Act: -0.0001

Data Index: 789548 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.6595. Min Act: -0.0001

Data Index: 293683 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.6629. Min Act: -0.0001

Data Index: 1086518 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.6914. Min Act: -0.0001

Data Index: 570772 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1273797 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.6538. Min Act: -0.0001

Data Index: 1242940 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.5914. Min Act: -0.0001

Data Index: 951076 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.8050. Min Range: -0.8050

Max Act: 0.6574. Min Act: -0.0001

Data Index: 1089708 (C4 (Web Text))

Max Activating Token Index: 191