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

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

Neuron 4949 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: 4.9784. Min Range: -4.9784

Max Act: 4.8072. Min Act: -0.0000

Data Index: 181866 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.9784. Min Act: -0.0000

Data Index: 1270253 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.5993. Min Act: -0.0001

Data Index: 881105 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.7560. Min Act: -0.0001

Data Index: 368837 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.0417. Min Act: -0.0000

Data Index: 1193601 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.3992. Min Act: -0.0001

Data Index: 631376 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.3694. Min Act: -0.0001

Data Index: 183369 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.5943. Min Act: -0.0001

Data Index: 875346 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.0795. Min Act: -0.0000

Data Index: 242843 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.5500. Min Act: -0.0001

Data Index: 789194 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.1405. Min Act: -0.0001

Data Index: 1114422 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.1738. Min Act: -0.0000

Data Index: 675980 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 4.9784. Min Range: -4.9784

Max Act: 3.8289. Min Act: -0.0000

Data Index: 225995 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.1237. Min Act: -0.0000

Data Index: 652999 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.6128. Min Act: -0.0000

Data Index: 684014 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.5967. Min Act: -0.0001

Data Index: 544476 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.4266. Min Act: -0.0001

Data Index: 545411 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.7495. Min Act: -0.0001

Data Index: 1042003 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.0471. Min Act: -0.0000

Data Index: 1132958 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 4.9784. Min Range: -4.9784

Max Act: 4.1917. Min Act: -0.0001

Data Index: 448865 (C4 (Web Text))

Max Activating Token Index: 499