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

Dataset: The Pile

Neuron 1081 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: 1.4542. Min Range: -1.4542

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1615711 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.3471. Min Act: -0.0000

Data Index: 83788 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.3907. Min Act: -0.0000

Data Index: 1983477 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2567. Min Act: -0.0000

Data Index: 981993 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1842503 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1151277 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.3241. Min Act: -0.0000

Data Index: 977301 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1902731 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1567. Min Act: -0.0000

Data Index: 972869 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.3342. Min Act: -0.0000

Data Index: 752745 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1825. Min Act: -0.0000

Data Index: 1371861 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1778197 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1551. Min Act: -0.0000

Data Index: 829057 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1333. Min Act: -0.0000

Data Index: 1450300 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2151. Min Act: -0.0000

Data Index: 1344429 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1280. Min Act: -0.0000

Data Index: 71525 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1882864 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1465899 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1337147 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1646. Min Act: -0.0000

Data Index: 844141 (The Pile)

Max Activating Token Index: 903