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

Dataset: The Pile

Neuron 3551 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.9064. Min Act: 0.0000

Data Index: 800254 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7859. Min Act: -0.0000

Data Index: 671534 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1919569 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7173. Min Act: -0.0000

Data Index: 329668 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1674339 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1989630 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6702. Min Act: -0.0000

Data Index: 917395 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1456655 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6829. Min Act: -0.0000

Data Index: 998750 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1558427 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1517683 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7084. Min Act: -0.0000

Data Index: 536425 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6758. Min Act: 0.0000

Data Index: 1678475 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1261609 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6450. Min Act: -0.0000

Data Index: 284398 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1130970 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6073. Min Act: -0.0000

Data Index: 135580 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1555414 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5972. Min Act: 0.0000

Data Index: 437328 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5891. Min Act: 0.0000

Data Index: 423499 (The Pile)

Max Activating Token Index: 920