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

Dataset: The Pile

Neuron 1417 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: 1.8271. Min Range: -1.8271

Max Act: 1.7772. Min Act: -0.0000

Data Index: 356786 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.7332. Min Act: -0.0000

Data Index: 438539 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.8271. Min Act: -0.0000

Data Index: 727771 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.6941. Min Act: -0.0000

Data Index: 976530 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.6824. Min Act: -0.0000

Data Index: 708589 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.6405. Min Act: -0.0000

Data Index: 696437 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.6284. Min Act: -0.0000

Data Index: 1725015 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.6032. Min Act: -0.0000

Data Index: 202035 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5082. Min Act: -0.0000

Data Index: 347800 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.7473. Min Act: -0.0000

Data Index: 1506433 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5735. Min Act: -0.0000

Data Index: 1088300 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5663. Min Act: -0.0000

Data Index: 981509 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1561315 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5501. Min Act: -0.0000

Data Index: 485303 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1612292 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5264. Min Act: -0.0000

Data Index: 706120 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.5208. Min Act: -0.0000

Data Index: 1350182 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.4865. Min Act: -0.0000

Data Index: 1535157 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.4016. Min Act: -0.0000

Data Index: 3472 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 1.8271. Min Range: -1.8271

Max Act: 1.4951. Min Act: -0.0000

Data Index: 1935962 (The Pile)

Max Activating Token Index: 222