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

Dataset: The Pile

Neuron 3592 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: 0.8398. Min Range: -0.8398

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1165664 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.8398. Min Act: -0.0000

Data Index: 348603 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1135542 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.8042. Min Act: -0.0000

Data Index: 889393 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7789. Min Act: -0.0000

Data Index: 623556 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7616. Min Act: -0.0000

Data Index: 933425 (The Pile)

Max Activating Token Index: 347

Text #6

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7809. Min Act: -0.0000

Data Index: 472434 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.8005. Min Act: -0.0000

Data Index: 100202 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1473708 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1571383 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1597996 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7191. Min Act: -0.0000

Data Index: 700590 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1356909 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.6986. Min Act: -0.0000

Data Index: 712108 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.6545. Min Act: -0.0000

Data Index: 938420 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1972282 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1396590 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7637. Min Act: -0.0000

Data Index: 67081 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7109. Min Act: -0.0000

Data Index: 64944 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.8398. Min Range: -0.8398

Max Act: 0.7576. Min Act: -0.0000

Data Index: 883836 (The Pile)

Max Activating Token Index: 506