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

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

Neuron 1064 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.8562. Min Act: -0.0000

Data Index: 773355 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.6976. Min Act: -0.0000

Data Index: 1214157 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.4364. Min Act: -0.0000

Data Index: 1026130 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.3555. Min Act: -0.0000

Data Index: 1018872 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.2608. Min Act: -0.0000

Data Index: 581192 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.3751. Min Act: -0.0000

Data Index: 1450519 (Python Code)

Max Activating Token Index: 576

Text #6

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.2505. Min Act: -0.0000

Data Index: 1404537 (Python Code)

Max Activating Token Index: 494

Text #7

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.1264. Min Act: -0.0000

Data Index: 1531667 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.2368. Min Act: -0.0000

Data Index: 431020 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.0781. Min Act: -0.0000

Data Index: 1549324 (Python Code)

Max Activating Token Index: 891

Text #10

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.3068. Min Act: -0.0000

Data Index: 737956 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.0591. Min Act: -0.0000

Data Index: 1400112 (Python Code)

Max Activating Token Index: 156

Text #12

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.1797. Min Act: -0.0000

Data Index: 508042 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.1441. Min Act: -0.0000

Data Index: 1617622 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.0355. Min Act: -0.0000

Data Index: 1635937 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.0250. Min Act: -0.0000

Data Index: 1548342 (Python Code)

Max Activating Token Index: 570

Text #16

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.1261. Min Act: -0.0000

Data Index: 231979 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.1150. Min Act: -0.0000

Data Index: 471791 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.0956. Min Act: -0.0000

Data Index: 1647198 (Python Code)

Max Activating Token Index: 496

Text #19

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.0965. Min Act: -0.0000

Data Index: 1621036 (Python Code)

Max Activating Token Index: 701