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

Dataset: The Pile

Neuron 3457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.9318. Min Act: -0.0000

Data Index: 344623 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7552. Min Act: -0.0000

Data Index: 820549 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1061911 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1435335 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.8241. Min Act: -0.0000

Data Index: 571096 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1190904 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1351723 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.8161. Min Act: -0.0000

Data Index: 252396 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.8061. Min Act: -0.0000

Data Index: 741656 (The Pile)

Max Activating Token Index: 804

Text #9

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1980744 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1269657 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1389138 (The Pile)

Max Activating Token Index: 1005

Text #12

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7813. Min Act: -0.0000

Data Index: 263366 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7612. Min Act: -0.0000

Data Index: 475151 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1978254 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1442092 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1968163 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7665. Min Act: -0.0000

Data Index: 390510 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1231908 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1479567 (The Pile)

Max Activating Token Index: 951