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

Dataset: The Pile

Neuron 1205 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: 0.1913. Min Range: -0.1913

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1495625 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1810. Min Act: -0.0000

Data Index: 572560 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1363245 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1672. Min Act: -0.0000

Data Index: 524061 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1516. Min Act: -0.0000

Data Index: 602367 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1093582 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1000093 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1459. Min Act: -0.0000

Data Index: 491796 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1314438 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1519. Min Act: -0.0000

Data Index: 613174 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1376520 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1711850 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1646. Min Act: -0.0000

Data Index: 400701 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1494. Min Act: -0.0000

Data Index: 248241 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1639420 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1512. Min Act: -0.0000

Data Index: 253445 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1211194 (The Pile)

Max Activating Token Index: 258

Text #17

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1627104 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1427. Min Act: -0.0000

Data Index: 38059 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1521. Min Act: -0.0000

Data Index: 246017 (The Pile)

Max Activating Token Index: 501