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

Dataset: The Pile

Neuron 4804 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: 1.1524. Min Range: -1.1524

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1263978 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1764326 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.1524. Min Act: -0.0000

Data Index: 1040021 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.0346. Min Act: -0.0000

Data Index: 731956 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.8747. Min Act: -0.0000

Data Index: 11559 (The Pile)

Max Activating Token Index: 475

Text #5

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1953022 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1142319 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.8346. Min Act: -0.0000

Data Index: 621454 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.8099. Min Act: -0.0000

Data Index: 36832 (The Pile)

Max Activating Token Index: 104

Text #9

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1360419 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1871479 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1404497 (The Pile)

Max Activating Token Index: 763

Text #12

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1893323 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1000231 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.8230. Min Act: -0.0000

Data Index: 85431 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7260. Min Act: -0.0000

Data Index: 115833 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7470. Min Act: -0.0000

Data Index: 648363 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1602532 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1967974 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.7208. Min Act: -0.0000

Data Index: 927402 (The Pile)

Max Activating Token Index: 1002