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

Dataset: The Pile

Neuron 3605 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.9835. Min Act: -0.0000

Data Index: 761667 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.9127. Min Act: -0.0000

Data Index: 744247 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1184350 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.8101. Min Act: -0.0000

Data Index: 878536 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.7542. Min Act: -0.0000

Data Index: 565714 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.8673. Min Act: -0.0000

Data Index: 1085888 (The Pile)

Max Activating Token Index: 809

Text #6

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.8658. Min Act: -0.0000

Data Index: 604636 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6982. Min Act: -0.0000

Data Index: 804798 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.7761. Min Act: -0.0000

Data Index: 209355 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1677900 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.7318. Min Act: -0.0000

Data Index: 1297499 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.8305. Min Act: -0.0000

Data Index: 1115960 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6992. Min Act: -0.0000

Data Index: 522244 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.7094. Min Act: -0.0000

Data Index: 108201 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1865394 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.8430. Min Act: -0.0000

Data Index: 268495 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.7147. Min Act: -0.0000

Data Index: 959830 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6136. Min Act: -0.0000

Data Index: 1335031 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1519410 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1957545 (The Pile)

Max Activating Token Index: 737