Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2789 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.9854. Min Act: -0.0000

Data Index: 647134 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.8392. Min Act: -0.0001

Data Index: 789439 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.7731. Min Act: -0.0001

Data Index: 600746 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.5733. Min Act: -0.0001

Data Index: 937042 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.6290. Min Act: -0.0001

Data Index: 883309 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.4857. Min Act: -0.0001

Data Index: 367682 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.4879. Min Act: -0.0001

Data Index: 1235568 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.4645. Min Act: -0.0001

Data Index: 955407 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.4469. Min Act: -0.0001

Data Index: 303998 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.5066. Min Act: -0.0001

Data Index: 617863 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.4351. Min Act: -0.0001

Data Index: 1092775 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1124777 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.4390. Min Act: -0.0001

Data Index: 1344843 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.3324. Min Act: -0.0001

Data Index: 1191451 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.3806. Min Act: -0.0000

Data Index: 445587 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.3245. Min Act: -0.0001

Data Index: 856912 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.4517. Min Act: -0.0001

Data Index: 360335 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.3167. Min Act: -0.0001

Data Index: 108723 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.3551. Min Act: -0.0001

Data Index: 423272 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.9854. Min Range: -1.9854

Max Act: 1.3449. Min Act: -0.0001

Data Index: 879285 (C4 (Web Text))

Max Activating Token Index: 860