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

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

Neuron 3955 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0268. Min Range: -6.0268

Max Act: 6.0268. Min Act: -0.0000

Data Index: 609749 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.7872. Min Act: -0.0000

Data Index: 502953 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.3434. Min Act: -0.0000

Data Index: 44028 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.5520. Min Act: -0.0000

Data Index: 89884 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.3107. Min Act: -0.0000

Data Index: 951931 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.4528. Min Act: -0.0000

Data Index: 776912 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.4461. Min Act: -0.0000

Data Index: 131073 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.1705. Min Act: -0.0000

Data Index: 222356 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.0164. Min Act: -0.0000

Data Index: 1057053 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.0448. Min Act: -0.0000

Data Index: 77780 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.0939. Min Act: -0.0000

Data Index: 526867 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 6.0268. Min Range: -6.0268

Max Act: 4.9140. Min Act: -0.0000

Data Index: 258884 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 6.0268. Min Range: -6.0268

Max Act: 5.2032. Min Act: -0.0000

Data Index: 88033 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 6.0268. Min Range: -6.0268

Max Act: 4.9855. Min Act: -0.0000

Data Index: 498860 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 6.0268. Min Range: -6.0268

Max Act: 4.8787. Min Act: -0.0000

Data Index: 477351 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 6.0268. Min Range: -6.0268

Max Act: 4.8987. Min Act: -0.0000

Data Index: 928812 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 6.0268. Min Range: -6.0268

Max Act: 4.8276. Min Act: -0.0000

Data Index: 276665 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 6.0268. Min Range: -6.0268

Max Act: 4.6074. Min Act: -0.0000

Data Index: 680738 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 6.0268. Min Range: -6.0268

Max Act: 4.7191. Min Act: -0.0000

Data Index: 375555 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 6.0268. Min Range: -6.0268

Max Act: 4.6966. Min Act: -0.0000

Data Index: 49958 (C4 (Web Text))

Max Activating Token Index: 365