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

Dataset: The Pile

Neuron 2757 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: 0.6134. Min Range: -0.6134

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1212602 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1446712 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1650841 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1815831 (The Pile)

Max Activating Token Index: 298

Text #4

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5550. Min Act: -0.0000

Data Index: 466353 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4983. Min Act: -0.0000

Data Index: 884640 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1492456 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5512. Min Act: -0.0000

Data Index: 85940 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1745409 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4397. Min Act: -0.0000

Data Index: 676893 (The Pile)

Max Activating Token Index: 235

Text #10

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4951. Min Act: -0.0000

Data Index: 435196 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4770. Min Act: -0.0000

Data Index: 611534 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1371066 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1358338 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1063842 (The Pile)

Max Activating Token Index: 530

Text #15

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1985263 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5011. Min Act: -0.0000

Data Index: 866039 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4615. Min Act: -0.0000

Data Index: 512058 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1437105 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4781. Min Act: -0.0000

Data Index: 280481 (The Pile)

Max Activating Token Index: 523