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

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

Neuron 3723 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5764. Min Range: -5.5764

Max Act: 5.5764. Min Act: -0.0001

Data Index: 215294 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 5.5764. Min Range: -5.5764

Max Act: 5.2083. Min Act: -0.0001

Data Index: 295918 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 5.5764. Min Range: -5.5764

Max Act: 5.3435. Min Act: -0.0001

Data Index: 369253 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.9328. Min Act: -0.0001

Data Index: 816279 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 5.5764. Min Range: -5.5764

Max Act: 5.0082. Min Act: -0.0001

Data Index: 1234293 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 5.5764. Min Range: -5.5764

Max Act: 5.1746. Min Act: -0.0001

Data Index: 1023803 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.8329. Min Act: -0.0001

Data Index: 947685 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.8058. Min Act: -0.0001

Data Index: 850383 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.4226. Min Act: -0.0001

Data Index: 1147300 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.8874. Min Act: -0.0001

Data Index: 1014544 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.4725. Min Act: -0.0001

Data Index: 167574 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 5.5764. Min Range: -5.5764

Max Act: 5.0167. Min Act: -0.0001

Data Index: 600972 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.4200. Min Act: -0.0001

Data Index: 685172 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.5330. Min Act: -0.0001

Data Index: 1187049 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.3227. Min Act: -0.0001

Data Index: 1158608 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.2953. Min Act: -0.0001

Data Index: 1126759 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.0783. Min Act: -0.0001

Data Index: 1308136 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.1331. Min Act: -0.0001

Data Index: 402100 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 5.5764. Min Range: -5.5764

Max Act: 4.3108. Min Act: -0.0001

Data Index: 388698 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 5.5764. Min Range: -5.5764

Max Act: 3.9859. Min Act: -0.0001

Data Index: 108728 (C4 (Web Text))

Max Activating Token Index: 344