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

Dataset: The Pile

Neuron 4701 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2448. Min Range: -3.2448

Max Act: 3.2448. Min Act: -0.0000

Data Index: 840830 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.8142. Min Act: -0.0000

Data Index: 1949034 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 3.2448. Min Range: -3.2448

Max Act: 3.0767. Min Act: -0.0000

Data Index: 127994 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.9128. Min Act: -0.0000

Data Index: 231231 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.6802. Min Act: -0.0000

Data Index: 595267 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.7958. Min Act: -0.0000

Data Index: 746691 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.6068. Min Act: -0.0000

Data Index: 482416 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.6784. Min Act: -0.0000

Data Index: 83856 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.4157. Min Act: -0.0000

Data Index: 1301342 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.5081. Min Act: -0.0000

Data Index: 1570698 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.2826. Min Act: -0.0000

Data Index: 1445745 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.4607. Min Act: -0.0000

Data Index: 328268 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.2703. Min Act: -0.0000

Data Index: 1780038 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.3008. Min Act: -0.0000

Data Index: 1960564 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.0226. Min Act: -0.0000

Data Index: 216419 (The Pile)

Max Activating Token Index: 746

Text #15

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.2388. Min Act: -0.0000

Data Index: 7749 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.2357. Min Act: -0.0000

Data Index: 1588074 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 3.2448. Min Range: -3.2448

Max Act: 1.9763. Min Act: -0.0000

Data Index: 552092 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.1291. Min Act: -0.0000

Data Index: 1075736 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 3.2448. Min Range: -3.2448

Max Act: 2.2416. Min Act: -0.0000

Data Index: 1527645 (The Pile)

Max Activating Token Index: 81