Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4731 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1349822 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4511. Min Act: -0.0001

Data Index: 912217 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1339797 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1018336 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1512345 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4129. Min Act: -0.0000

Data Index: 100564 (The Pile)

Max Activating Token Index: 594

Text #6

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1098940 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.4018. Min Act: -0.0000

Data Index: 219533 (The Pile)

Max Activating Token Index: 614

Text #8

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3697. Min Act: -0.0000

Data Index: 636476 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3407. Min Act: -0.0000

Data Index: 63527 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1057264 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3746. Min Act: -0.0000

Data Index: 13388 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1330052 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1546054 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3583. Min Act: -0.0000

Data Index: 167201 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1483601 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3241. Min Act: -0.0000

Data Index: 534082 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3128. Min Act: -0.0000

Data Index: 793780 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1889005 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 0.5166. Min Range: -0.5166

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1145568 (The Pile)

Max Activating Token Index: 995