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

Dataset: The Pile

Neuron 2117 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6933. Min Act: -0.0000

Data Index: 104492 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6625. Min Act: -0.0000

Data Index: 879010 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1005877 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1952626 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1635651 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1067682 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5637. Min Act: -0.0000

Data Index: 626776 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5807. Min Act: -0.0000

Data Index: 386761 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5693. Min Act: -0.0000

Data Index: 295037 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1908552 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.4917. Min Act: -0.0000

Data Index: 338794 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1173753 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1219078 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5834. Min Act: -0.0000

Data Index: 920835 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1972618 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5215. Min Act: -0.0000

Data Index: 518121 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5528. Min Act: -0.0000

Data Index: 86385 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5410. Min Act: -0.0000

Data Index: 139418 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5316. Min Act: -0.0000

Data Index: 980889 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.6933. Min Range: -0.6933

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1392238 (The Pile)

Max Activating Token Index: 974