Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 678 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1634. Min Range: -1.1634

Max Act: 1.1356. Min Act: -0.0001

Data Index: 1054043 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.1634. Min Range: -1.1634

Max Act: 1.1634. Min Act: -0.0001

Data Index: 346567 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.9766. Min Act: -0.0001

Data Index: 548740 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.9702. Min Act: -0.0001

Data Index: 441858 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.9848. Min Act: -0.0001

Data Index: 541887 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.9166. Min Act: -0.0001

Data Index: 527118 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.1634. Min Range: -1.1634

Max Act: 1.0166. Min Act: -0.0001

Data Index: 135184 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.9484. Min Act: -0.0001

Data Index: 606088 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.9020. Min Act: -0.0001

Data Index: 519149 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.8337. Min Act: -0.0001

Data Index: 21543 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.7924. Min Act: -0.0001

Data Index: 758354 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.8384. Min Act: -0.0001

Data Index: 285135 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.8486. Min Act: -0.0001

Data Index: 774298 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.7881. Min Act: -0.0001

Data Index: 1267924 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.9261. Min Act: -0.0001

Data Index: 277067 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.8131. Min Act: -0.0001

Data Index: 329953 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.8672. Min Act: -0.0001

Data Index: 356342 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.8335. Min Act: -0.0001

Data Index: 471342 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.8112. Min Act: -0.0001

Data Index: 498107 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 1.1634. Min Range: -1.1634

Max Act: 0.7238. Min Act: -0.0001

Data Index: 675666 (C4 (Web Text))

Max Activating Token Index: 225