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

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

Neuron 5549 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0918. Min Range: -6.0918

Max Act: 6.0918. Min Act: -0.0000

Data Index: 1069830 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 6.0918. Min Range: -6.0918

Max Act: 5.0087. Min Act: -0.0000

Data Index: 1317448 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.9503. Min Act: -0.0000

Data Index: 1273442 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.7787. Min Act: -0.0000

Data Index: 1132047 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.6060. Min Act: -0.0000

Data Index: 698990 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.5892. Min Act: -0.0000

Data Index: 141121 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.5436. Min Act: -0.0000

Data Index: 530563 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.3271. Min Act: -0.0000

Data Index: 415048 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.4438. Min Act: -0.0000

Data Index: 441707 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.4036. Min Act: -0.0000

Data Index: 1253984 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.5098. Min Act: -0.0000

Data Index: 1246361 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.4301. Min Act: -0.0000

Data Index: 696494 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.4200. Min Act: -0.0000

Data Index: 1050308 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 6.0918. Min Range: -6.0918

Max Act: 4.1476. Min Act: -0.0000

Data Index: 1210787 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 6.0918. Min Range: -6.0918

Max Act: 3.9502. Min Act: -0.0000

Data Index: 1221332 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 6.0918. Min Range: -6.0918

Max Act: 3.8411. Min Act: -0.0000

Data Index: 698224 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 6.0918. Min Range: -6.0918

Max Act: 3.6471. Min Act: -0.0000

Data Index: 792289 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 6.0918. Min Range: -6.0918

Max Act: 3.6946. Min Act: -0.0000

Data Index: 1314294 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 6.0918. Min Range: -6.0918

Max Act: 3.7746. Min Act: -0.0000

Data Index: 732901 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 6.0918. Min Range: -6.0918

Max Act: 3.6657. Min Act: -0.0000

Data Index: 1141631 (C4 (Web Text))

Max Activating Token Index: 352