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

Dataset: The Pile

Neuron 504 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.5738. Min Act: -0.0000

Data Index: 281724 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1389168 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.3688. Min Act: -0.0000

Data Index: 401633 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1210218 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.4771. Min Act: -0.0000

Data Index: 1011582 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.3843. Min Act: -0.0000

Data Index: 1440586 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1602896 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.2505. Min Act: -0.0000

Data Index: 955309 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.2283. Min Act: -0.0000

Data Index: 265228 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1703541 (The Pile)

Max Activating Token Index: 196

Text #10

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.2097. Min Act: -0.0000

Data Index: 685252 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.0959. Min Act: -0.0000

Data Index: 293190 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.0844. Min Act: -0.0000

Data Index: 62638 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.0956. Min Act: -0.0000

Data Index: 184895 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.0442. Min Act: -0.0000

Data Index: 554109 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.0410. Min Act: -0.0000

Data Index: 456735 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1905 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.0517. Min Act: -0.0000

Data Index: 918131 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.1172. Min Act: -0.0000

Data Index: 330317 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 1.5738. Min Range: -1.5738

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1535757 (The Pile)

Max Activating Token Index: 290