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

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

Neuron 503 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5482. Min Act: -0.0001

Data Index: 1648682 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5213. Min Act: -0.0001

Data Index: 1624730 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5560. Min Act: -0.0001

Data Index: 1564848 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5258. Min Act: -0.0001

Data Index: 1461624 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1594574 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4870. Min Act: -0.0001

Data Index: 1407805 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4967. Min Act: -0.0001

Data Index: 1262811 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4706. Min Act: -0.0001

Data Index: 1560436 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4858. Min Act: -0.0001

Data Index: 1370446 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4706. Min Act: -0.0001

Data Index: 1492583 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4705. Min Act: -0.0001

Data Index: 1643516 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1037738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1518111 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4602. Min Act: -0.0001

Data Index: 1407838 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1425956 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4434. Min Act: -0.0001

Data Index: 1001358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4544. Min Act: -0.0001

Data Index: 1589434 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4379. Min Act: -0.0001

Data Index: 1624979 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4507. Min Act: -0.0001

Data Index: 876599 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4494. Min Act: -0.0001

Data Index: 41309 (C4 (Web Text))

Max Activating Token Index: 1023