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

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

Neuron 4802 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.5730. Min Act: -0.0000

Data Index: 458102 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.5935. Min Act: -0.0000

Data Index: 840511 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.5493. Min Act: 0.0000

Data Index: 676494 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.5354. Min Act: -0.0000

Data Index: 935788 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4938. Min Act: -0.0000

Data Index: 266037 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.5099. Min Act: -0.0000

Data Index: 231990 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4742. Min Act: -0.0000

Data Index: 875967 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4608. Min Act: 0.0000

Data Index: 547683 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4514. Min Act: -0.0000

Data Index: 451305 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4544. Min Act: -0.0000

Data Index: 554995 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1307179 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4516. Min Act: -0.0000

Data Index: 75800 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4488. Min Act: -0.0000

Data Index: 508340 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4410. Min Act: -0.0000

Data Index: 537413 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4320. Min Act: -0.0000

Data Index: 314726 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4130. Min Act: -0.0000

Data Index: 143730 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4254. Min Act: -0.0000

Data Index: 674205 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4356. Min Act: -0.0000

Data Index: 95101 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.4451. Min Act: -0.0000

Data Index: 66258 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.5935. Min Range: -0.5935

Max Act: 0.3905. Min Act: 0.0000

Data Index: 531849 (C4 (Web Text))

Max Activating Token Index: 643