Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2427 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1484688 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7456. Min Act: -0.0000

Data Index: 757226 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1108961 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1403237 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6764. Min Act: -0.0000

Data Index: 79963 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1811004 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1433679 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1596416 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7388. Min Act: -0.0000

Data Index: 391251 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6068. Min Act: -0.0001

Data Index: 1051553 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1231105 (The Pile)

Max Activating Token Index: 550

Text #11

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7393. Min Act: -0.0000

Data Index: 865125 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1889850 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7147. Min Act: -0.0000

Data Index: 335782 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1872787 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7582. Min Act: -0.0000

Data Index: 363272 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1726581 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6466. Min Act: -0.0001

Data Index: 1215017 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6382. Min Act: -0.0000

Data Index: 518196 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1497246 (The Pile)

Max Activating Token Index: 295