Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2662 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1192. Min Range: -2.1192

Max Act: 2.1192. Min Act: -0.0000

Data Index: 379545 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.9880. Min Act: -0.0000

Data Index: 1643419 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.8278. Min Act: -0.0000

Data Index: 1520813 (Python Code)

Max Activating Token Index: 253

Text #3

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6716. Min Act: -0.0000

Data Index: 1531194 (Python Code)

Max Activating Token Index: 531

Text #4

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.8356. Min Act: -0.0000

Data Index: 262202 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.7221. Min Act: -0.0000

Data Index: 150302 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.7313. Min Act: -0.0000

Data Index: 645992 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6368. Min Act: -0.0001

Data Index: 1620800 (Python Code)

Max Activating Token Index: 674

Text #8

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6990. Min Act: -0.0001

Data Index: 443355 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6494. Min Act: -0.0000

Data Index: 964344 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6624. Min Act: -0.0000

Data Index: 1386087 (Python Code)

Max Activating Token Index: 115

Text #11

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6454. Min Act: -0.0000

Data Index: 1038222 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6074. Min Act: -0.0000

Data Index: 1398088 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6134. Min Act: -0.0000

Data Index: 225059 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.5339. Min Act: -0.0000

Data Index: 1489117 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1655806 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.4676. Min Act: -0.0000

Data Index: 80681 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1543231 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.4455. Min Act: -0.0000

Data Index: 236094 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 2.1192. Min Range: -2.1192

Max Act: 1.6075. Min Act: -0.0000

Data Index: 1634830 (Python Code)

Max Activating Token Index: 788