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

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

Neuron 572 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.6691. Min Act: -0.0002

Data Index: 145040 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4641. Min Act: -0.0002

Data Index: 890290 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4578. Min Act: -0.0002

Data Index: 605061 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4510. Min Act: -0.0002

Data Index: 538109 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4762. Min Act: -0.0002

Data Index: 1054146 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4187. Min Act: -0.0002

Data Index: 432705 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3806. Min Act: -0.0002

Data Index: 926029 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4371. Min Act: -0.0002

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4052. Min Act: -0.0002

Data Index: 1150612 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3512. Min Act: -0.0002

Data Index: 959962 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3706. Min Act: -0.0002

Data Index: 1034936 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3727. Min Act: -0.0002

Data Index: 725739 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3527. Min Act: -0.0002

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3328. Min Act: -0.0002

Data Index: 977264 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3750. Min Act: -0.0002

Data Index: 837801 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3474. Min Act: -0.0002

Data Index: 1284141 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3515. Min Act: -0.0002

Data Index: 50085 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3610. Min Act: -0.0002

Data Index: 106785 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3110. Min Act: -0.0002

Data Index: 793690 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3255. Min Act: -0.0002

Data Index: 834240 (C4 (Web Text))

Max Activating Token Index: 865