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

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

Neuron 1660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.4078. Min Act: -0.0000

Data Index: 10713 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3866. Min Act: -0.0000

Data Index: 372115 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3710. Min Act: -0.0000

Data Index: 535011 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3528. Min Act: -0.0000

Data Index: 499622 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1326053 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3259. Min Act: -0.0000

Data Index: 324779 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1239697 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3490. Min Act: -0.0000

Data Index: 759768 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3332. Min Act: -0.0000

Data Index: 239132 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3227. Min Act: -0.0000

Data Index: 273982 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3097. Min Act: -0.0000

Data Index: 186413 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3261. Min Act: -0.0000

Data Index: 647098 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3076. Min Act: -0.0000

Data Index: 359137 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3095. Min Act: -0.0000

Data Index: 706486 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2875. Min Act: -0.0000

Data Index: 308632 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1117693 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2867. Min Act: -0.0000

Data Index: 217594 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2823. Min Act: -0.0000

Data Index: 663377 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2897. Min Act: -0.0000

Data Index: 251926 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1141983 (C4 (Web Text))

Max Activating Token Index: 900