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

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

Neuron 2826 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: 1.0147. Min Range: -1.0147

Max Act: 0.9872. Min Act: -0.0001

Data Index: 794668 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.9388. Min Act: -0.0001

Data Index: 351835 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.9442. Min Act: -0.0001

Data Index: 178314 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 1.0147. Min Range: -1.0147

Max Act: 1.0147. Min Act: -0.0001

Data Index: 1228149 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.9354. Min Act: -0.0001

Data Index: 179231 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.9581. Min Act: -0.0001

Data Index: 1238521 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.9268. Min Act: -0.0001

Data Index: 1054095 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8928. Min Act: -0.0001

Data Index: 254649 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8921. Min Act: -0.0001

Data Index: 739813 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8954. Min Act: -0.0001

Data Index: 708187 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8887. Min Act: -0.0001

Data Index: 652481 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8103. Min Act: -0.0001

Data Index: 273716 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.9066. Min Act: -0.0001

Data Index: 867970 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8982. Min Act: -0.0001

Data Index: 1189484 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.9143. Min Act: -0.0001

Data Index: 1259535 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8502. Min Act: -0.0001

Data Index: 825906 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.9004. Min Act: -0.0001

Data Index: 968025 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8615. Min Act: -0.0001

Data Index: 627269 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8773. Min Act: -0.0001

Data Index: 147928 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8495. Min Act: -0.0001

Data Index: 698405 (C4 (Web Text))

Max Activating Token Index: 728