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

Dataset: The Pile

Neuron 374 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.4140. Min Act: -0.0000

Data Index: 803025 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.3771. Min Act: -0.0000

Data Index: 945169 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2783. Min Act: -0.0000

Data Index: 155671 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2490. Min Act: -0.0000

Data Index: 69090 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1312688 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2492. Min Act: -0.0000

Data Index: 720439 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1236573 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1108417 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1845843 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1165790 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1907. Min Act: -0.0000

Data Index: 960029 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1068890 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1442543 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1648194 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1225098 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1120255 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1740. Min Act: -0.0000

Data Index: 775849 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1812209 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1278442 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.4140. Min Range: -0.4140

Max Act: 0.1716. Min Act: -0.0000

Data Index: 9802 (The Pile)

Max Activating Token Index: 100