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

Dataset: The Pile

Neuron 405 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: 0.9129. Min Range: -0.9129

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1870175 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1559028 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8589. Min Act: -0.0000

Data Index: 868260 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8939. Min Act: -0.0000

Data Index: 563833 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1031730 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7579. Min Act: -0.0000

Data Index: 396077 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1687818 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7388. Min Act: -0.0000

Data Index: 628874 (The Pile)

Max Activating Token Index: 810

Text #8

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8132. Min Act: -0.0000

Data Index: 662064 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1064731 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7652. Min Act: -0.0000

Data Index: 673544 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1294446 (The Pile)

Max Activating Token Index: 14

Text #12

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.8343. Min Act: -0.0000

Data Index: 62497 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1242241 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7047. Min Act: -0.0000

Data Index: 813517 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7406. Min Act: -0.0000

Data Index: 882548 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7431. Min Act: -0.0000

Data Index: 341927 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1794191 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7427. Min Act: -0.0000

Data Index: 197891 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7828. Min Act: -0.0000

Data Index: 644002 (The Pile)

Max Activating Token Index: 905