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

Dataset: The Pile

Neuron 3957 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.9134. Min Act: -0.0000

Data Index: 303274 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.4445. Min Act: -0.0000

Data Index: 674297 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.7290. Min Act: -0.0000

Data Index: 1535725 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.8082. Min Act: -0.0000

Data Index: 1789020 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.6043. Min Act: -0.0000

Data Index: 316040 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.5879. Min Act: -0.0000

Data Index: 1207176 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.3891. Min Act: -0.0000

Data Index: 934292 (The Pile)

Max Activating Token Index: 464

Text #7

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.5603. Min Act: -0.0000

Data Index: 1257704 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.5458. Min Act: -0.0000

Data Index: 881088 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.5375. Min Act: -0.0000

Data Index: 1936971 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.3545. Min Act: -0.0000

Data Index: 847521 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.3175. Min Act: -0.0000

Data Index: 1300054 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.1407. Min Act: -0.0000

Data Index: 1930085 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.2724. Min Act: -0.0000

Data Index: 1863206 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.4504. Min Act: -0.0000

Data Index: 92935 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.3120. Min Act: -0.0000

Data Index: 1885776 (The Pile)

Max Activating Token Index: 952

Text #16

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.3746. Min Act: -0.0000

Data Index: 1847716 (The Pile)

Max Activating Token Index: 496

Text #17

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.3705. Min Act: -0.0000

Data Index: 47798 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.3386. Min Act: -0.0000

Data Index: 1317216 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 3.9134. Min Range: -3.9134

Max Act: 3.3520. Min Act: -0.0000

Data Index: 652371 (The Pile)

Max Activating Token Index: 114