Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1281 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.7540. Min Act: -0.0000

Data Index: 688311 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.9184. Min Act: -0.0001

Data Index: 24105 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.6947. Min Act: -0.0000

Data Index: 22902 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.6624. Min Act: -0.0001

Data Index: 246380 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.7459. Min Act: -0.0000

Data Index: 45844 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.5492. Min Act: -0.0000

Data Index: 1136545 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.8481. Min Act: -0.0001

Data Index: 636018 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.4786. Min Act: -0.0000

Data Index: 254313 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.5637. Min Act: -0.0001

Data Index: 205157 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.6668. Min Act: -0.0000

Data Index: 385838 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.4900. Min Act: -0.0001

Data Index: 240745 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.4849. Min Act: -0.0000

Data Index: 316422 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.5252. Min Act: -0.0001

Data Index: 560518 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.4878. Min Act: -0.0000

Data Index: 1191402 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1192812 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.4263. Min Act: -0.0001

Data Index: 1138941 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.3447. Min Act: -0.0000

Data Index: 731864 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.3708. Min Act: -0.0000

Data Index: 831248 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.5240. Min Act: -0.0000

Data Index: 557576 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.9184. Min Range: -1.9184

Max Act: 1.3540. Min Act: -0.0001

Data Index: 717111 (C4 (Web Text))

Max Activating Token Index: 413