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

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

Neuron 920 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: 5.1386. Min Range: -5.1386

Max Act: 5.1386. Min Act: -0.0000

Data Index: 1315686 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 5.1386. Min Range: -5.1386

Max Act: 4.6739. Min Act: -0.0000

Data Index: 746255 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 5.1386. Min Range: -5.1386

Max Act: 4.1201. Min Act: -0.0000

Data Index: 564457 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.7634. Min Act: -0.0000

Data Index: 639388 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 5.1386. Min Range: -5.1386

Max Act: 4.0106. Min Act: -0.0000

Data Index: 1067677 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.9825. Min Act: -0.0000

Data Index: 980052 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.5907. Min Act: -0.0000

Data Index: 183901 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.6420. Min Act: -0.0000

Data Index: 707560 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.4787. Min Act: -0.0000

Data Index: 130985 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.4381. Min Act: -0.0000

Data Index: 257106 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.4892. Min Act: -0.0000

Data Index: 359 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.4378. Min Act: -0.0000

Data Index: 548022 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.3722. Min Act: -0.0000

Data Index: 706892 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.3316. Min Act: -0.0000

Data Index: 209908 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.5174. Min Act: -0.0000

Data Index: 309417 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.1080. Min Act: -0.0000

Data Index: 1015670 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.3781. Min Act: -0.0000

Data Index: 1114511 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.2198. Min Act: -0.0000

Data Index: 716873 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 5.1386. Min Range: -5.1386

Max Act: 3.0428. Min Act: -0.0000

Data Index: 682399 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 5.1386. Min Range: -5.1386

Max Act: 2.7299. Min Act: -0.0000

Data Index: 937482 (C4 (Web Text))

Max Activating Token Index: 29