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

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

Neuron 990 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: 7.0766. Min Range: -7.0766

Max Act: 7.0766. Min Act: -0.0000

Data Index: 544475 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 7.0766. Min Range: -7.0766

Max Act: 6.9779. Min Act: -0.0000

Data Index: 1107067 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 7.0766. Min Range: -7.0766

Max Act: 6.0738. Min Act: -0.0000

Data Index: 435926 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.8657. Min Act: -0.0000

Data Index: 440649 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.7896. Min Act: -0.0000

Data Index: 854901 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.8962. Min Act: -0.0000

Data Index: 644623 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.5021. Min Act: -0.0000

Data Index: 349044 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.4484. Min Act: -0.0000

Data Index: 999610 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.2188. Min Act: -0.0000

Data Index: 57866 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.7844. Min Act: -0.0000

Data Index: 190740 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.4907. Min Act: -0.0000

Data Index: 1271637 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.6651. Min Act: -0.0000

Data Index: 1003207 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.4232. Min Act: -0.0000

Data Index: 614087 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.2324. Min Act: -0.0000

Data Index: 632338 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.2710. Min Act: -0.0000

Data Index: 1230126 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 7.0766. Min Range: -7.0766

Max Act: 5.2241. Min Act: -0.0000

Data Index: 86294 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 7.0766. Min Range: -7.0766

Max Act: 4.7868. Min Act: -0.0000

Data Index: 91608 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 7.0766. Min Range: -7.0766

Max Act: 4.7212. Min Act: -0.0000

Data Index: 1160449 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 7.0766. Min Range: -7.0766

Max Act: 4.9181. Min Act: -0.0000

Data Index: 1265792 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 7.0766. Min Range: -7.0766

Max Act: 4.5161. Min Act: -0.0000

Data Index: 657042 (C4 (Web Text))

Max Activating Token Index: 525