Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3867 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6764. Min Act: -0.0000

Data Index: 710309 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6633. Min Act: -0.0000

Data Index: 770544 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5386. Min Act: -0.0000

Data Index: 173489 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1609837 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4347. Min Act: -0.0000

Data Index: 284612 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1003712 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1464410 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1454316 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1603919 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1411006 (Python Code)

Max Activating Token Index: 291

Text #10

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1467876 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1496530 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4384. Min Act: -0.0000

Data Index: 471837 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4500. Min Act: -0.0000

Data Index: 455190 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1643898 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4144. Min Act: -0.0000

Data Index: 235630 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1605806 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1535533 (Python Code)

Max Activating Token Index: 84

Text #18

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1366137 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1631873 (Python Code)

Max Activating Token Index: 102