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

Dataset: The Pile

Neuron 3415 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.4438. Min Act: -0.0000

Data Index: 251146 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1062060 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3740. Min Act: -0.0000

Data Index: 355763 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1092341 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3347. Min Act: 0.0000

Data Index: 1485748 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3323. Min Act: -0.0000

Data Index: 589709 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3260. Min Act: -0.0000

Data Index: 701578 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1208172 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3074. Min Act: -0.0000

Data Index: 206714 (The Pile)

Max Activating Token Index: 95

Text #9

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2955. Min Act: -0.0000

Data Index: 839508 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2983. Min Act: -0.0000

Data Index: 74015 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2926. Min Act: -0.0000

Data Index: 359369 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1718326 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2914. Min Act: -0.0000

Data Index: 924934 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1978366 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2773. Min Act: -0.0000

Data Index: 329213 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1103990 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2737. Min Act: -0.0000

Data Index: 709004 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1165124 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2640. Min Act: -0.0000

Data Index: 591472 (The Pile)

Max Activating Token Index: 76