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

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

Neuron 2952 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8486. Min Act: -0.0003

Data Index: 424355 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8494. Min Act: -0.0003

Data Index: 1356782 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8581. Min Act: -0.0003

Data Index: 1164022 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8251. Min Act: -0.0003

Data Index: 1161916 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7708. Min Act: -0.0003

Data Index: 631018 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8080. Min Act: -0.0003

Data Index: 1077441 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8029. Min Act: -0.0003

Data Index: 279193 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8058. Min Act: -0.0003

Data Index: 299174 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8020. Min Act: -0.0003

Data Index: 598199 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7787. Min Act: -0.0003

Data Index: 796495 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7965. Min Act: -0.0003

Data Index: 455413 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7691. Min Act: -0.0003

Data Index: 532234 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7416. Min Act: -0.0003

Data Index: 393430 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7862. Min Act: -0.0003

Data Index: 559479 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6859. Min Act: -0.0003

Data Index: 375824 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7336. Min Act: -0.0003

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6135. Min Act: -0.0003

Data Index: 590916 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7633. Min Act: -0.0003

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7551. Min Act: -0.0003

Data Index: 61612 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8215. Min Act: -0.0003

Data Index: 129679 (C4 (Web Text))

Max Activating Token Index: 271