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

Dataset: The Pile

Neuron 866 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0605. Min Range: -1.0605

Max Act: 1.0605. Min Act: -0.0000

Data Index: 619582 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1901164 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1271916 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1287173 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1662562 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7074. Min Act: -0.0000

Data Index: 420862 (The Pile)

Max Activating Token Index: 769

Text #6

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1791978 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6529. Min Act: -0.0000

Data Index: 37084 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1053573 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1045977 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1245888 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1336175 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1393367 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6348. Min Act: -0.0000

Data Index: 646147 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1946057 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1326217 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1425493 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1096789 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1012039 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.5760. Min Act: -0.0000

Data Index: 894242 (The Pile)

Max Activating Token Index: 733