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

Dataset: The Pile

Neuron 2375 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: 6.2773. Min Range: -6.2773

Max Act: 6.2773. Min Act: -0.0000

Data Index: 1831484 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.8891. Min Act: -0.0000

Data Index: 1391842 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.8382. Min Act: -0.0000

Data Index: 1707526 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.7167. Min Act: -0.0000

Data Index: 1402081 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.8688. Min Act: -0.0000

Data Index: 1364474 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.4249. Min Act: -0.0000

Data Index: 1946944 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.9970. Min Act: -0.0000

Data Index: 1482167 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.5582. Min Act: -0.0000

Data Index: 266887 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 6.2773. Min Range: -6.2773

Max Act: 4.7869. Min Act: -0.0000

Data Index: 1075682 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.2549. Min Act: -0.0000

Data Index: 684081 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.4882. Min Act: -0.0000

Data Index: 1188806 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.3024. Min Act: -0.0000

Data Index: 996969 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.4476. Min Act: -0.0000

Data Index: 1527505 (The Pile)

Max Activating Token Index: 957

Text #13

Max Range: 6.2773. Min Range: -6.2773

Max Act: 4.7918. Min Act: -0.0000

Data Index: 1564916 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.0759. Min Act: -0.0000

Data Index: 1392019 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 6.2773. Min Range: -6.2773

Max Act: 4.7462. Min Act: -0.0000

Data Index: 1953773 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.0561. Min Act: -0.0000

Data Index: 741731 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 6.2773. Min Range: -6.2773

Max Act: 5.0067. Min Act: -0.0000

Data Index: 579140 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 6.2773. Min Range: -6.2773

Max Act: 4.8512. Min Act: -0.0000

Data Index: 784596 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 6.2773. Min Range: -6.2773

Max Act: 4.9929. Min Act: -0.0000

Data Index: 1948255 (The Pile)

Max Activating Token Index: 526