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

Dataset: The Pile

Neuron 3155 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1015176 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3289. Min Act: -0.0000

Data Index: 640809 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1013137 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3045. Min Act: -0.0000

Data Index: 714336 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2873. Min Act: -0.0000

Data Index: 41488 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2681. Min Act: -0.0000

Data Index: 690625 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1575357 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2904. Min Act: -0.0000

Data Index: 927482 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1876503 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1652563 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2872. Min Act: -0.0000

Data Index: 283968 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2601. Min Act: -0.0000

Data Index: 392199 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1571572 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2645. Min Act: -0.0000

Data Index: 131785 (The Pile)

Max Activating Token Index: 201

Text #14

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2666. Min Act: -0.0000

Data Index: 817423 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2710. Min Act: -0.0000

Data Index: 396185 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1391867 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2721. Min Act: -0.0000

Data Index: 341277 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1584511 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2679. Min Act: -0.0000

Data Index: 321189 (The Pile)

Max Activating Token Index: 1021