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

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

Neuron 5320 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1365601 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1566087 (Python Code)

Max Activating Token Index: 282

Text #2

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1432945 (Python Code)

Max Activating Token Index: 264

Text #3

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1410896 (Python Code)

Max Activating Token Index: 822

Text #4

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1494236 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1550962 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1503642 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1386158 (Python Code)

Max Activating Token Index: 611

Text #8

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1544007 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1462735 (Python Code)

Max Activating Token Index: 404

Text #10

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1402525 (Python Code)

Max Activating Token Index: 675

Text #11

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1621104 (Python Code)

Max Activating Token Index: 877

Text #12

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1400623 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1426454 (Python Code)

Max Activating Token Index: 439

Text #14

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1532073 (Python Code)

Max Activating Token Index: 769

Text #15

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1622109 (Python Code)

Max Activating Token Index: 870

Text #16

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1569374 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1567105 (Python Code)

Max Activating Token Index: 478

Text #18

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1372417 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1438041 (Python Code)

Max Activating Token Index: 611