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

Dataset: The Pile

Neuron 1682 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: 0.6330. Min Range: -0.6330

Max Act: 0.5662. Min Act: -0.0000

Data Index: 10488 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1150567 (The Pile)

Max Activating Token Index: 689

Text #2

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1946836 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5934. Min Act: -0.0000

Data Index: 75211 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1679430 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1631168 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1641739 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5093. Min Act: -0.0000

Data Index: 747411 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1080662 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1035888 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1026075 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5420. Min Act: -0.0000

Data Index: 577 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1535770 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1182110 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1952453 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5011. Min Act: -0.0000

Data Index: 85306 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1725851 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1805662 (The Pile)

Max Activating Token Index: 65

Text #18

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1338158 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4882. Min Act: -0.0000

Data Index: 712613 (The Pile)

Max Activating Token Index: 370