Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1912 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.9320. Min Act: -0.0001

Data Index: 612768 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.7970. Min Act: -0.0001

Data Index: 505129 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.7824. Min Act: -0.0001

Data Index: 1223763 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8501. Min Act: -0.0001

Data Index: 513548 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.7307. Min Act: -0.0001

Data Index: 246750 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.7771. Min Act: -0.0001

Data Index: 352080 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.7647. Min Act: -0.0001

Data Index: 169572 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.7180. Min Act: -0.0001

Data Index: 65396 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.6502. Min Act: -0.0001

Data Index: 1251302 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.6954. Min Act: -0.0001

Data Index: 970780 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.6830. Min Act: -0.0001

Data Index: 739799 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.7156. Min Act: -0.0001

Data Index: 488033 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.6527. Min Act: -0.0001

Data Index: 465359 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.7049. Min Act: -0.0001

Data Index: 1310339 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.6035. Min Act: -0.0001

Data Index: 873931 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8728. Min Act: -0.0001

Data Index: 914015 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.5779. Min Act: -0.0001

Data Index: 31212 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.5745. Min Act: -0.0001

Data Index: 269997 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.5714. Min Act: -0.0001

Data Index: 1089437 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.6565. Min Act: -0.0001

Data Index: 709758 (C4 (Web Text))

Max Activating Token Index: 519