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

Dataset: The Pile

Neuron 1189 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: 1.2094. Min Range: -1.2094

Max Act: 1.2094. Min Act: -0.0000

Data Index: 1389007 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1567. Min Act: -0.0000

Data Index: 511700 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1828226 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9766. Min Act: -0.0000

Data Index: 267254 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1249237 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1206560 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1333927 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9255. Min Act: -0.0000

Data Index: 127527 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8939. Min Act: -0.0000

Data Index: 171528 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9460. Min Act: -0.0000

Data Index: 999584 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1463955 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9555. Min Act: -0.0000

Data Index: 133424 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1614176 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1653634 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1647259 (The Pile)

Max Activating Token Index: 95

Text #15

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.7992. Min Act: -0.0000

Data Index: 344767 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8089. Min Act: -0.0000

Data Index: 297129 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8412. Min Act: -0.0000

Data Index: 182135 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8316. Min Act: -0.0000

Data Index: 977744 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8073. Min Act: -0.0000

Data Index: 182377 (The Pile)

Max Activating Token Index: 845