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

Dataset: The Pile

Neuron 613 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.3144. Min Act: -0.0000

Data Index: 1453769 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.2535. Min Act: -0.0000

Data Index: 1036346 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8168. Min Act: -0.0000

Data Index: 248208 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.0522. Min Act: -0.0000

Data Index: 1222892 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.1635. Min Act: -0.0000

Data Index: 1626540 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.2828. Min Act: -0.0000

Data Index: 1620968 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.1388. Min Act: -0.0000

Data Index: 1579204 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.9773. Min Act: -0.0000

Data Index: 1017719 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.0474. Min Act: -0.0000

Data Index: 754010 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.0323. Min Act: -0.0000

Data Index: 661102 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8919. Min Act: -0.0000

Data Index: 308702 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.7460. Min Act: -0.0000

Data Index: 1287805 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8859. Min Act: -0.0000

Data Index: 374779 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8824. Min Act: -0.0000

Data Index: 778805 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8595. Min Act: -0.0000

Data Index: 1748242 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 3.3144. Min Range: -3.3144

Max Act: 3.1055. Min Act: -0.0000

Data Index: 1082817 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.9679. Min Act: -0.0000

Data Index: 497109 (The Pile)

Max Activating Token Index: 647

Text #17

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.9624. Min Act: -0.0000

Data Index: 1336489 (The Pile)

Max Activating Token Index: 420

Text #18

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.8869. Min Act: -0.0000

Data Index: 1512704 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 3.3144. Min Range: -3.3144

Max Act: 2.7634. Min Act: -0.0000

Data Index: 1725505 (The Pile)

Max Activating Token Index: 364