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

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

Neuron 5128 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0525. Min Range: -5.0525

Max Act: 5.0525. Min Act: -0.0000

Data Index: 782294 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.6696. Min Act: -0.0000

Data Index: 351019 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.4541. Min Act: -0.0000

Data Index: 191257 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.1876. Min Act: -0.0000

Data Index: 1058899 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.2049. Min Act: -0.0000

Data Index: 632713 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.1540. Min Act: -0.0000

Data Index: 817617 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.1273. Min Act: -0.0000

Data Index: 86470 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.1196. Min Act: -0.0000

Data Index: 670262 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.0509. Min Act: -0.0000

Data Index: 297156 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 5.0525. Min Range: -5.0525

Max Act: 4.0196. Min Act: -0.0000

Data Index: 201093 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.9995. Min Act: -0.0000

Data Index: 793658 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.8265. Min Act: -0.0000

Data Index: 638325 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.7898. Min Act: -0.0000

Data Index: 258593 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.9079. Min Act: -0.0000

Data Index: 611134 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.8959. Min Act: -0.0000

Data Index: 101232 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.8874. Min Act: -0.0000

Data Index: 1098523 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.8846. Min Act: -0.0000

Data Index: 308317 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.8709. Min Act: -0.0000

Data Index: 109393 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.9960. Min Act: -0.0000

Data Index: 693497 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 5.0525. Min Range: -5.0525

Max Act: 3.6613. Min Act: -0.0000

Data Index: 1586 (C4 (Web Text))

Max Activating Token Index: 913