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

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

Neuron 4775 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.7505. Min Act: -0.0000

Data Index: 659222 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.7274. Min Act: -0.0000

Data Index: 84003 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6767. Min Act: -0.0000

Data Index: 773271 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6712. Min Act: -0.0000

Data Index: 877392 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1254572 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6813. Min Act: -0.0000

Data Index: 75871 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6410. Min Act: -0.0000

Data Index: 87440 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1219419 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1168716 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1054279 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6560. Min Act: -0.0000

Data Index: 147303 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6362. Min Act: 0.0000

Data Index: 423639 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6317. Min Act: -0.0000

Data Index: 432304 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6543. Min Act: -0.0000

Data Index: 918088 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6966. Min Act: -0.0000

Data Index: 475910 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6030. Min Act: -0.0000

Data Index: 670157 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6492. Min Act: -0.0000

Data Index: 979892 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6442. Min Act: -0.0000

Data Index: 633601 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6548. Min Act: -0.0000

Data Index: 58612 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.7505. Min Range: -0.7505

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1093996 (C4 (Web Text))

Max Activating Token Index: 558