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

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

Neuron 3165 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: 1.1994. Min Range: -1.1994

Max Act: 1.1994. Min Act: -0.0000

Data Index: 427929 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.1994. Min Range: -1.1994

Max Act: 1.1682. Min Act: -0.0000

Data Index: 1270327 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.1994. Min Range: -1.1994

Max Act: 1.0797. Min Act: -0.0000

Data Index: 629585 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.1994. Min Range: -1.1994

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1140624 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1548977 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.9507. Min Act: -0.0000

Data Index: 521367 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1377523 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.8185. Min Act: -0.0000

Data Index: 903446 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1478997 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1512257 (Python Code)

Max Activating Token Index: 496

Text #10

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.6918. Min Act: -0.0000

Data Index: 240309 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1454482 (Python Code)

Max Activating Token Index: 145

Text #12

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1621376 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.6321. Min Act: -0.0000

Data Index: 521778 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1612064 (Python Code)

Max Activating Token Index: 710

Text #15

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1458671 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1449524 (Python Code)

Max Activating Token Index: 398

Text #17

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1617361 (Python Code)

Max Activating Token Index: 216

Text #18

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5855. Min Act: -0.0000

Data Index: 932393 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.1994. Min Range: -1.1994

Max Act: 0.5030. Min Act: -0.0000

Data Index: 445173 (C4 (Web Text))

Max Activating Token Index: 685