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

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

Neuron 1273 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: 0.8809. Min Range: -0.8809

Max Act: 0.8809. Min Act: -0.0000

Data Index: 745662 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8413. Min Act: -0.0001

Data Index: 1405830 (Python Code)

Max Activating Token Index: 990

Text #2

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8044. Min Act: -0.0001

Data Index: 1604873 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1485780 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7382. Min Act: -0.0001

Data Index: 1578574 (Python Code)

Max Activating Token Index: 394

Text #5

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7254. Min Act: -0.0001

Data Index: 1618827 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7730. Min Act: -0.0001

Data Index: 103730 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7732. Min Act: -0.0001

Data Index: 1408704 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7395. Min Act: -0.0001

Data Index: 1645116 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1598933 (Python Code)

Max Activating Token Index: 429

Text #10

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7411. Min Act: -0.0001

Data Index: 1632339 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7316. Min Act: -0.0001

Data Index: 1370662 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6968. Min Act: -0.0001

Data Index: 1511478 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6906. Min Act: -0.0001

Data Index: 1549939 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7035. Min Act: -0.0000

Data Index: 41281 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.7031. Min Act: -0.0001

Data Index: 1552903 (Python Code)

Max Activating Token Index: 928

Text #16

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1246074 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6999. Min Act: -0.0000

Data Index: 132653 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6964. Min Act: -0.0001

Data Index: 729433 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6943. Min Act: -0.0001

Data Index: 891307 (C4 (Web Text))

Max Activating Token Index: 308