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

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

Neuron 3007 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6681. Min Act: -0.0000

Data Index: 767880 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1561285 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1366490 (Python Code)

Max Activating Token Index: 473

Text #3

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5779. Min Act: -0.0000

Data Index: 883655 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1377449 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1469228 (Python Code)

Max Activating Token Index: 478

Text #6

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5794. Min Act: -0.0000

Data Index: 792622 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1032696 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5577. Min Act: -0.0000

Data Index: 95519 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5792. Min Act: -0.0000

Data Index: 138525 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5693. Min Act: -0.0000

Data Index: 338238 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4823. Min Act: -0.0000

Data Index: 616026 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1215755 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1378713 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1512977 (Python Code)

Max Activating Token Index: 372

Text #15

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5039. Min Act: -0.0000

Data Index: 336936 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1578316 (Python Code)

Max Activating Token Index: 859

Text #17

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4977. Min Act: -0.0000

Data Index: 108 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5124. Min Act: -0.0000

Data Index: 698618 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5060. Min Act: -0.0000

Data Index: 99787 (C4 (Web Text))

Max Activating Token Index: 959