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

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

Neuron 3449 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.8365. Min Act: -0.0000

Data Index: 444099 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.6263. Min Act: -0.0000

Data Index: 474728 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.6247. Min Act: -0.0000

Data Index: 265134 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.6056. Min Act: -0.0000

Data Index: 1225582 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.5308. Min Act: -0.0000

Data Index: 191636 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.3892. Min Act: -0.0000

Data Index: 913768 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.3254. Min Act: -0.0000

Data Index: 1025213 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.2110. Min Act: -0.0000

Data Index: 270066 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.2095. Min Act: -0.0000

Data Index: 272517 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.1935. Min Act: -0.0000

Data Index: 1108641 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.1383. Min Act: -0.0000

Data Index: 831285 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.1135. Min Act: -0.0000

Data Index: 1042128 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.2634. Min Act: -0.0000

Data Index: 378070 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.0793. Min Act: -0.0000

Data Index: 812456 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.0658. Min Act: -0.0000

Data Index: 1276661 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.2139. Min Act: -0.0000

Data Index: 296085 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.0375. Min Act: -0.0000

Data Index: 1034993 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 3.8365. Min Range: -3.8365

Max Act: 3.0113. Min Act: -0.0000

Data Index: 661479 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 3.8365. Min Range: -3.8365

Max Act: 2.9999. Min Act: -0.0000

Data Index: 393987 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.8365. Min Range: -3.8365

Max Act: 2.9814. Min Act: -0.0000

Data Index: 1275903 (C4 (Web Text))

Max Activating Token Index: 768