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

Dataset: The Pile

Neuron 3122 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.9400. Min Act: -0.0000

Data Index: 181595 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7706. Min Act: -0.0001

Data Index: 1543807 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1875671 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7856. Min Act: -0.0000

Data Index: 917653 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7623. Min Act: -0.0000

Data Index: 424380 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7973. Min Act: -0.0000

Data Index: 353968 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6761. Min Act: -0.0000

Data Index: 884139 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6661. Min Act: -0.0000

Data Index: 43367 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7126. Min Act: -0.0000

Data Index: 456141 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1151328 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6895. Min Act: -0.0000

Data Index: 919541 (The Pile)

Max Activating Token Index: 407

Text #11

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1874156 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6298. Min Act: -0.0000

Data Index: 737357 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6255. Min Act: -0.0000

Data Index: 677560 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1662777 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1533762 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6419. Min Act: -0.0000

Data Index: 883740 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6546. Min Act: 0.0001

Data Index: 1411363 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6094. Min Act: -0.0000

Data Index: 345314 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 0.9400. Min Range: -0.9400

Max Act: 0.6311. Min Act: -0.0000

Data Index: 334010 (The Pile)

Max Activating Token Index: 448