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

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

Neuron 3050 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.7285. Min Act: -0.0000

Data Index: 1651492 (Python Code)

Max Activating Token Index: 430

Text #1

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.2554. Min Act: -0.0000

Data Index: 1386895 (Python Code)

Max Activating Token Index: 416

Text #2

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.2654. Min Act: -0.0000

Data Index: 1515992 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.1342. Min Act: -0.0000

Data Index: 1408942 (Python Code)

Max Activating Token Index: 574

Text #4

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.2492. Min Act: -0.0000

Data Index: 1653094 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.2337. Min Act: -0.0000

Data Index: 1411209 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.1658. Min Act: -0.0000

Data Index: 1493301 (Python Code)

Max Activating Token Index: 726

Text #7

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.1733. Min Act: -0.0000

Data Index: 1376396 (Python Code)

Max Activating Token Index: 930

Text #8

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.0486. Min Act: -0.0000

Data Index: 1366781 (Python Code)

Max Activating Token Index: 200

Text #9

Max Range: 4.7285. Min Range: -4.7285

Max Act: 3.6342. Min Act: -0.0000

Data Index: 1409217 (Python Code)

Max Activating Token Index: 149

Text #10

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.1983. Min Act: -0.0000

Data Index: 1422893 (Python Code)

Max Activating Token Index: 341

Text #11

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.1558. Min Act: -0.0000

Data Index: 1495388 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 4.7285. Min Range: -4.7285

Max Act: 3.9526. Min Act: -0.0000

Data Index: 1397443 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 4.7285. Min Range: -4.7285

Max Act: 3.9595. Min Act: -0.0000

Data Index: 1384808 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.0390. Min Act: -0.0000

Data Index: 1583559 (Python Code)

Max Activating Token Index: 68

Text #15

Max Range: 4.7285. Min Range: -4.7285

Max Act: 4.0199. Min Act: -0.0000

Data Index: 1361957 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 4.7285. Min Range: -4.7285

Max Act: 3.8894. Min Act: -0.0000

Data Index: 1653758 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 4.7285. Min Range: -4.7285

Max Act: 3.8498. Min Act: -0.0000

Data Index: 1560331 (Python Code)

Max Activating Token Index: 438

Text #18

Max Range: 4.7285. Min Range: -4.7285

Max Act: 3.9637. Min Act: -0.0000

Data Index: 1543057 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 4.7285. Min Range: -4.7285

Max Act: 3.7078. Min Act: -0.0000

Data Index: 1423016 (Python Code)

Max Activating Token Index: 86