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

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

Neuron 346 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: 1.4587. Min Range: -1.4587

Max Act: 1.4587. Min Act: -0.0002

Data Index: 171393 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.3705. Min Act: -0.0002

Data Index: 846512 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.3070. Min Act: -0.0002

Data Index: 238336 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2778. Min Act: -0.0002

Data Index: 963041 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2774. Min Act: -0.0003

Data Index: 378056 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2857. Min Act: -0.0002

Data Index: 48994 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2810. Min Act: -0.0002

Data Index: 1082597 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2711. Min Act: -0.0002

Data Index: 941952 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2576. Min Act: -0.0002

Data Index: 952148 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2684. Min Act: -0.0002

Data Index: 1029668 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.3181. Min Act: -0.0002

Data Index: 1189162 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2888. Min Act: -0.0002

Data Index: 723395 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2733. Min Act: -0.0002

Data Index: 507549 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2655. Min Act: -0.0002

Data Index: 289891 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2375. Min Act: -0.0002

Data Index: 904809 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2692. Min Act: -0.0002

Data Index: 558929 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2662. Min Act: -0.0002

Data Index: 964460 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2390. Min Act: -0.0002

Data Index: 1147352 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2270. Min Act: -0.0002

Data Index: 352613 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 1.4587. Min Range: -1.4587

Max Act: 1.2220. Min Act: -0.0003

Data Index: 923718 (C4 (Web Text))

Max Activating Token Index: 72