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

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

Neuron 1148 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.6493. Min Act: -0.0000

Data Index: 626283 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.6557. Min Act: -0.0000

Data Index: 836553 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5754. Min Act: -0.0000

Data Index: 881871 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5418. Min Act: -0.0000

Data Index: 210832 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5543. Min Act: -0.0000

Data Index: 489840 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5654. Min Act: -0.0000

Data Index: 398339 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5460. Min Act: -0.0000

Data Index: 881276 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1118140 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4958. Min Act: -0.0000

Data Index: 485079 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4947. Min Act: -0.0000

Data Index: 477808 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4871. Min Act: -0.0000

Data Index: 576131 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4992. Min Act: -0.0000

Data Index: 897632 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1124605 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1340680 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1210982 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4623. Min Act: -0.0000

Data Index: 371160 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4576. Min Act: -0.0000

Data Index: 942051 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4719. Min Act: -0.0000

Data Index: 228762 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4415. Min Act: -0.0000

Data Index: 454581 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4330. Min Act: -0.0000

Data Index: 596617 (C4 (Web Text))

Max Activating Token Index: 603