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

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

Neuron 5857 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: 3.3165. Min Range: -3.3165

Max Act: 3.3165. Min Act: -0.0000

Data Index: 1312323 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1973. Min Act: -0.0000

Data Index: 968933 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1869. Min Act: -0.0000

Data Index: 1359636 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1844. Min Act: -0.0000

Data Index: 780161 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0207. Min Act: -0.0000

Data Index: 999834 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0872. Min Act: -0.0000

Data Index: 1018702 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0705. Min Act: -0.0000

Data Index: 687579 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0406. Min Act: -0.0000

Data Index: 187385 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.8974. Min Act: -0.0000

Data Index: 1328371 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0387. Min Act: -0.0000

Data Index: 1274463 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1800. Min Act: -0.0000

Data Index: 167723 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.8283. Min Act: -0.0000

Data Index: 1155203 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.8218. Min Act: -0.0000

Data Index: 419081 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.9396. Min Act: -0.0000

Data Index: 971047 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.9387. Min Act: -0.0000

Data Index: 62896 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.7991. Min Act: -0.0000

Data Index: 169609 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.9391. Min Act: -0.0000

Data Index: 406702 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.9441. Min Act: -0.0000

Data Index: 1109352 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.9271. Min Act: -0.0000

Data Index: 791505 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 3.3165. Min Range: -3.3165

Max Act: 2.9270. Min Act: -0.0000

Data Index: 236591 (C4 (Web Text))

Max Activating Token Index: 385