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

Dataset: The Pile

Neuron 2958 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: 1.1440. Min Range: -1.1440

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1372489 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1400351 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1806390 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.1440. Min Range: -1.1440

Max Act: 1.0287. Min Act: -0.0000

Data Index: 40932 (The Pile)

Max Activating Token Index: 904

Text #4

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9668. Min Act: -0.0000

Data Index: 37134 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1977486 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1106104 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8748. Min Act: -0.0000

Data Index: 735238 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8417. Min Act: -0.0000

Data Index: 334950 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8833. Min Act: -0.0000

Data Index: 1760937 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8196. Min Act: -0.0000

Data Index: 729819 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.9224. Min Act: -0.0000

Data Index: 979120 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7161. Min Act: -0.0000

Data Index: 920328 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1977866 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7621. Min Act: -0.0000

Data Index: 767884 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1129793 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1316370 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1121986 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7954. Min Act: -0.0000

Data Index: 504869 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 1.1440. Min Range: -1.1440

Max Act: 0.7942. Min Act: -0.0000

Data Index: 885968 (The Pile)

Max Activating Token Index: 249