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

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

Neuron 698 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.8043. Min Act: -0.0001

Data Index: 1381811 (Python Code)

Max Activating Token Index: 829

Text #1

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.7979. Min Act: -0.0001

Data Index: 1517074 (Python Code)

Max Activating Token Index: 820

Text #2

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.7863. Min Act: -0.0000

Data Index: 118651 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6444. Min Act: -0.0001

Data Index: 1544749 (Python Code)

Max Activating Token Index: 382

Text #4

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6536. Min Act: -0.0000

Data Index: 839425 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1475797 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1464052 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1625600 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1445800 (Python Code)

Max Activating Token Index: 958

Text #9

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5659. Min Act: -0.0000

Data Index: 928579 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5746. Min Act: -0.0001

Data Index: 1501049 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5906. Min Act: -0.0001

Data Index: 1442680 (Python Code)

Max Activating Token Index: 385

Text #12

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1214414 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1625839 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5673. Min Act: -0.0001

Data Index: 1431431 (Python Code)

Max Activating Token Index: 477

Text #15

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1488844 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5773. Min Act: -0.0000

Data Index: 664118 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1459544 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1616968 (Python Code)

Max Activating Token Index: 416

Text #19

Max Range: 0.8043. Min Range: -0.8043

Max Act: 0.5132. Min Act: 0.0001

Data Index: 1582800 (Python Code)

Max Activating Token Index: 678