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

Dataset: The Pile

Neuron 1707 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: 0.6518. Min Range: -0.6518

Max Act: 0.6518. Min Act: -0.0000

Data Index: 719249 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1540164 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1699684 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5960. Min Act: -0.0000

Data Index: 647251 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5108. Min Act: -0.0000

Data Index: 788692 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1759822 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4643. Min Act: -0.0000

Data Index: 837105 (The Pile)

Max Activating Token Index: 625

Text #7

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1789026 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5256. Min Act: -0.0000

Data Index: 649875 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1800052 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1225262 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1602248 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4874. Min Act: -0.0000

Data Index: 74739 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1127543 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4536. Min Act: -0.0000

Data Index: 162967 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1138954 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4798. Min Act: -0.0000

Data Index: 328805 (The Pile)

Max Activating Token Index: 274

Text #17

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1801230 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4568. Min Act: -0.0000

Data Index: 373915 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1409671 (The Pile)

Max Activating Token Index: 477