Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3956 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4398. Min Act: -0.0000

Data Index: 732518 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4122. Min Act: -0.0000

Data Index: 910559 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3670. Min Act: -0.0000

Data Index: 265873 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3960. Min Act: -0.0000

Data Index: 184600 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3949. Min Act: -0.0001

Data Index: 1104481 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1140000 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3826. Min Act: -0.0001

Data Index: 1090283 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3667. Min Act: -0.0001

Data Index: 908879 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3639. Min Act: -0.0001

Data Index: 1154113 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3752. Min Act: -0.0000

Data Index: 655133 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3600. Min Act: -0.0000

Data Index: 777120 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3651. Min Act: -0.0001

Data Index: 1051307 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3654. Min Act: -0.0001

Data Index: 806587 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1271157 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3591. Min Act: -0.0000

Data Index: 169592 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3595. Min Act: -0.0000

Data Index: 730048 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3614. Min Act: -0.0001

Data Index: 411844 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1320703 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3575. Min Act: -0.0001

Data Index: 605071 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3424. Min Act: -0.0000

Data Index: 166525 (C4 (Web Text))

Max Activating Token Index: 939