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

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

Neuron 4431 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3894. Min Range: -7.3894

Max Act: 7.3894. Min Act: -0.0000

Data Index: 887965 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 7.3894. Min Range: -7.3894

Max Act: 7.1296. Min Act: -0.0000

Data Index: 616889 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.4330. Min Act: -0.0001

Data Index: 118995 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.3179. Min Act: -0.0000

Data Index: 528668 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 7.3894. Min Range: -7.3894

Max Act: 6.8288. Min Act: -0.0000

Data Index: 514924 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.8455. Min Act: -0.0000

Data Index: 137652 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.1315. Min Act: -0.0000

Data Index: 1125614 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.0378. Min Act: -0.0000

Data Index: 581612 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.4622. Min Act: -0.0000

Data Index: 648920 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 7.3894. Min Range: -7.3894

Max Act: 4.5198. Min Act: -0.0001

Data Index: 569767 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 7.3894. Min Range: -7.3894

Max Act: 4.6689. Min Act: -0.0000

Data Index: 824684 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 7.3894. Min Range: -7.3894

Max Act: 3.5126. Min Act: -0.0001

Data Index: 111779 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 7.3894. Min Range: -7.3894

Max Act: 4.5969. Min Act: -0.0000

Data Index: 715928 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 7.3894. Min Range: -7.3894

Max Act: 3.5648. Min Act: -0.0001

Data Index: 920030 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 7.3894. Min Range: -7.3894

Max Act: 4.5535. Min Act: -0.0000

Data Index: 431952 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 7.3894. Min Range: -7.3894

Max Act: 4.6365. Min Act: -0.0001

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 7.3894. Min Range: -7.3894

Max Act: 5.0990. Min Act: -0.0001

Data Index: 535086 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 7.3894. Min Range: -7.3894

Max Act: 4.3774. Min Act: -0.0001

Data Index: 890672 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 7.3894. Min Range: -7.3894

Max Act: 4.3664. Min Act: -0.0001

Data Index: 1203248 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 7.3894. Min Range: -7.3894

Max Act: 4.1369. Min Act: -0.0001

Data Index: 289740 (C4 (Web Text))

Max Activating Token Index: 35