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

Dataset: The Pile

Neuron 71 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: 1.1952. Min Range: -1.1952

Max Act: 1.1952. Min Act: -0.0000

Data Index: 549140 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9991. Min Act: -0.0000

Data Index: 310221 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9631. Min Act: -0.0000

Data Index: 196653 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1223652 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1437460 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.9072. Min Act: -0.0000

Data Index: 538639 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1539115 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8194. Min Act: -0.0000

Data Index: 126500 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1395445 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1518653 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1909756 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1196482 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.8001. Min Act: -0.0000

Data Index: 452844 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7960. Min Act: -0.0000

Data Index: 883691 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7314. Min Act: -0.0000

Data Index: 142733 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1611310 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1731994 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1981613 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.6791. Min Act: -0.0000

Data Index: 264706 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 1.1952. Min Range: -1.1952

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1046662 (The Pile)

Max Activating Token Index: 117