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

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

Neuron 4343 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: 1.3420. Min Range: -1.3420

Max Act: 1.3420. Min Act: -0.0002

Data Index: 1301185 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2962. Min Act: -0.0002

Data Index: 828440 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.3292. Min Act: -0.0002

Data Index: 1039128 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.3039. Min Act: -0.0002

Data Index: 658180 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2812. Min Act: -0.0002

Data Index: 705649 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2773. Min Act: -0.0002

Data Index: 346315 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2931. Min Act: -0.0002

Data Index: 946000 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2892. Min Act: -0.0002

Data Index: 761687 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2505. Min Act: -0.0002

Data Index: 388862 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2760. Min Act: -0.0002

Data Index: 272193 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2606. Min Act: -0.0002

Data Index: 304025 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2515. Min Act: -0.0002

Data Index: 185547 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2617. Min Act: -0.0002

Data Index: 946698 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2501. Min Act: -0.0002

Data Index: 1133461 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2647. Min Act: -0.0002

Data Index: 658934 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2443. Min Act: -0.0002

Data Index: 14062 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2347. Min Act: -0.0002

Data Index: 295411 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2292. Min Act: -0.0002

Data Index: 788402 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2264. Min Act: -0.0002

Data Index: 936841 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.3420. Min Range: -1.3420

Max Act: 1.2508. Min Act: -0.0002

Data Index: 231436 (C4 (Web Text))

Max Activating Token Index: 175