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

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

Neuron 5856 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6706. Min Range: -6.6706

Max Act: 6.6706. Min Act: -0.0000

Data Index: 278781 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 6.6706. Min Range: -6.6706

Max Act: 6.0687. Min Act: -0.0000

Data Index: 67541 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 6.6706. Min Range: -6.6706

Max Act: 5.3603. Min Act: -0.0000

Data Index: 20739 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.9961. Min Act: -0.0000

Data Index: 967026 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 6.6706. Min Range: -6.6706

Max Act: 5.2974. Min Act: -0.0000

Data Index: 926071 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.7466. Min Act: -0.0000

Data Index: 930499 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.8654. Min Act: -0.0000

Data Index: 183960 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 6.6706. Min Range: -6.6706

Max Act: 5.2259. Min Act: -0.0000

Data Index: 963763 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.8321. Min Act: -0.0000

Data Index: 20650 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.6122. Min Act: -0.0000

Data Index: 1151154 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.5831. Min Act: -0.0000

Data Index: 512951 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.7537. Min Act: -0.0000

Data Index: 1039675 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.3282. Min Act: -0.0000

Data Index: 802687 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.3148. Min Act: -0.0000

Data Index: 428876 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.4789. Min Act: -0.0000

Data Index: 685210 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.5996. Min Act: -0.0000

Data Index: 361475 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.2414. Min Act: -0.0000

Data Index: 573744 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.5531. Min Act: -0.0000

Data Index: 173520 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.2397. Min Act: -0.0000

Data Index: 429360 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 6.6706. Min Range: -6.6706

Max Act: 4.0805. Min Act: -0.0000

Data Index: 955885 (C4 (Web Text))

Max Activating Token Index: 70