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

Dataset: The Pile

Neuron 65 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: 7.2228. Min Range: -7.2228

Max Act: 7.2228. Min Act: -0.0000

Data Index: 1439464 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 7.2228. Min Range: -7.2228

Max Act: 4.1093. Min Act: -0.0000

Data Index: 542222 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.9225. Min Act: 0.0000

Data Index: 693891 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.8047. Min Act: 0.0001

Data Index: 1896480 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.4763. Min Act: 0.0000

Data Index: 540262 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.5752. Min Act: -0.0000

Data Index: 1898716 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.2899. Min Act: -0.0000

Data Index: 1424809 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.5233. Min Act: -0.0000

Data Index: 1228520 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.4803. Min Act: -0.0000

Data Index: 445411 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.6061. Min Act: -0.0000

Data Index: 959292 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.4042. Min Act: -0.0000

Data Index: 185920 (The Pile)

Max Activating Token Index: 59

Text #11

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.1103. Min Act: 0.0000

Data Index: 226961 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.2333. Min Act: -0.0000

Data Index: 52679 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.5045. Min Act: -0.0000

Data Index: 341504 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 7.2228. Min Range: -7.2228

Max Act: 2.9485. Min Act: -0.0000

Data Index: 1155447 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.2448. Min Act: -0.0000

Data Index: 1205993 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.1009. Min Act: -0.0000

Data Index: 1859263 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.0822. Min Act: -0.0000

Data Index: 313630 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 7.2228. Min Range: -7.2228

Max Act: 2.8954. Min Act: 0.0000

Data Index: 486268 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 7.2228. Min Range: -7.2228

Max Act: 3.1243. Min Act: -0.0000

Data Index: 1930999 (The Pile)

Max Activating Token Index: 496