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

Dataset: The Pile

Neuron 4258 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.7387. Min Act: -0.0000

Data Index: 692379 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1310859 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1504942 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1185116 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1782909 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.4898. Min Act: -0.0000

Data Index: 291191 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.3090. Min Act: -0.0000

Data Index: 707284 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.5351. Min Act: -0.0000

Data Index: 1043286 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.4322. Min Act: -0.0000

Data Index: 254185 (The Pile)

Max Activating Token Index: 362

Text #9

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1680941 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.4876. Min Act: -0.0000

Data Index: 333033 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.4156. Min Act: -0.0000

Data Index: 982079 (The Pile)

Max Activating Token Index: 487

Text #12

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.5740. Min Act: -0.0000

Data Index: 1881239 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1717560 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.3902. Min Act: -0.0000

Data Index: 1209255 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1283582 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.3138. Min Act: -0.0000

Data Index: 236491 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.3768. Min Act: -0.0000

Data Index: 886909 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.2879. Min Act: -0.0000

Data Index: 1686633 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 1.7765. Min Range: -1.7765

Max Act: 1.2848. Min Act: -0.0000

Data Index: 937481 (The Pile)

Max Activating Token Index: 35