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

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

Neuron 3655 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.9198. Min Act: -0.0000

Data Index: 609046 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.7111. Min Act: -0.0000

Data Index: 112924 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1129681 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6711. Min Act: -0.0000

Data Index: 406250 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.6409. Min Act: -0.0000

Data Index: 603494 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5963. Min Act: -0.0000

Data Index: 549571 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5804. Min Act: -0.0000

Data Index: 790238 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1298518 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5793. Min Act: -0.0000

Data Index: 227710 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5249. Min Act: -0.0000

Data Index: 735705 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5542. Min Act: 0.0000

Data Index: 831970 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5546. Min Act: -0.0000

Data Index: 592027 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5656. Min Act: -0.0000

Data Index: 319383 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.4948. Min Act: -0.0000

Data Index: 466158 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.4490. Min Act: -0.0000

Data Index: 650178 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5572. Min Act: -0.0000

Data Index: 920723 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.4658. Min Act: -0.0000

Data Index: 685223 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5307. Min Act: -0.0000

Data Index: 269894 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1058906 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.9198. Min Range: -0.9198

Max Act: 0.4902. Min Act: -0.0000

Data Index: 871733 (C4 (Web Text))

Max Activating Token Index: 528