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

Dataset: The Pile

Neuron 1303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4455. Min Act: -0.0000

Data Index: 951836 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3453. Min Act: -0.0000

Data Index: 642392 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4360. Min Act: -0.0000

Data Index: 626818 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4843. Min Act: -0.0000

Data Index: 64905 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4367. Min Act: -0.0001

Data Index: 404582 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3639. Min Act: -0.0000

Data Index: 390319 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1700358 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4410. Min Act: -0.0000

Data Index: 521860 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1436777 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1660360 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4276. Min Act: -0.0000

Data Index: 417760 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3895. Min Act: -0.0000

Data Index: 156392 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3828. Min Act: -0.0000

Data Index: 697224 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1116414 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1231877 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4094. Min Act: -0.0000

Data Index: 526178 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1666395 (The Pile)

Max Activating Token Index: 898

Text #17

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1722586 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1457271 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1713377 (The Pile)

Max Activating Token Index: 239