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

Dataset: The Pile

Neuron 2437 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: 4.2199. Min Range: -4.2199

Max Act: 4.2199. Min Act: -0.0000

Data Index: 632147 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.6859. Min Act: -0.0000

Data Index: 1747547 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.5490. Min Act: -0.0000

Data Index: 884562 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.4955. Min Act: -0.0000

Data Index: 647224 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.5274. Min Act: -0.0000

Data Index: 1054871 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.4559. Min Act: -0.0000

Data Index: 1665403 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.2496. Min Act: -0.0000

Data Index: 17528 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.1701. Min Act: -0.0000

Data Index: 865272 (The Pile)

Max Activating Token Index: 968

Text #8

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.3420. Min Act: -0.0000

Data Index: 673611 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.1088. Min Act: -0.0000

Data Index: 153904 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.0624. Min Act: -0.0000

Data Index: 409399 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.2175. Min Act: -0.0000

Data Index: 1901372 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.1963. Min Act: -0.0000

Data Index: 264666 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.3381. Min Act: -0.0000

Data Index: 1306498 (The Pile)

Max Activating Token Index: 383

Text #14

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.0164. Min Act: -0.0000

Data Index: 365744 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 4.2199. Min Range: -4.2199

Max Act: 2.9945. Min Act: -0.0000

Data Index: 390226 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.0783. Min Act: -0.0000

Data Index: 916893 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 4.2199. Min Range: -4.2199

Max Act: 2.7927. Min Act: -0.0000

Data Index: 407598 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 4.2199. Min Range: -4.2199

Max Act: 3.0453. Min Act: -0.0000

Data Index: 685574 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 4.2199. Min Range: -4.2199

Max Act: 2.7357. Min Act: -0.0000

Data Index: 1594222 (The Pile)

Max Activating Token Index: 830