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

Dataset: The Pile

Neuron 1189 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: 1.6276. Min Range: -1.6276

Max Act: 1.6276. Min Act: -0.0000

Data Index: 820045 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.5804. Min Act: -0.0000

Data Index: 595709 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1419397 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.5229. Min Act: -0.0000

Data Index: 450232 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.4401. Min Act: -0.0000

Data Index: 1286018 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.3336. Min Act: -0.0000

Data Index: 517117 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.2435. Min Act: -0.0000

Data Index: 761279 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.2712. Min Act: -0.0000

Data Index: 625871 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.2554. Min Act: -0.0000

Data Index: 984359 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.2524. Min Act: -0.0000

Data Index: 785686 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1640818 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.2752. Min Act: -0.0000

Data Index: 384060 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.1590. Min Act: -0.0000

Data Index: 812787 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.1562. Min Act: -0.0000

Data Index: 544731 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.1007. Min Act: -0.0000

Data Index: 519732 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1254065 (The Pile)

Max Activating Token Index: 83

Text #16

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1058548 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1884829 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.1155. Min Act: -0.0000

Data Index: 156897 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.1119. Min Act: -0.0000

Data Index: 708561 (The Pile)

Max Activating Token Index: 197