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

Dataset: The Pile

Neuron 3498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1161831 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.6159. Min Act: -0.0000

Data Index: 402350 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.5770. Min Act: -0.0000

Data Index: 1969180 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1887576 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1199949 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2745. Min Act: -0.0000

Data Index: 909714 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1599753 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1146818 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2073. Min Act: -0.0000

Data Index: 415100 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1219127 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2604. Min Act: -0.0000

Data Index: 528896 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1368662 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1509060 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1909070 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.1968. Min Act: -0.0000

Data Index: 806612 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.1212. Min Act: -0.0000

Data Index: 914033 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1262762 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.1286. Min Act: -0.0000

Data Index: 133299 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.1268. Min Act: -0.0000

Data Index: 504203 (The Pile)

Max Activating Token Index: 210

Text #19

Max Range: 1.6530. Min Range: -1.6530

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1432471 (The Pile)

Max Activating Token Index: 348