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

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

Neuron 4611 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1620881 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1465417 (Python Code)

Max Activating Token Index: 138

Text #2

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1633838 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1075243 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.9896. Min Act: -0.0001

Data Index: 256957 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.9996. Min Act: -0.0001

Data Index: 1620064 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.9562. Min Act: -0.0001

Data Index: 1411879 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.9209. Min Act: -0.0000

Data Index: 748344 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.9462. Min Act: -0.0001

Data Index: 1628868 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1439432 (Python Code)

Max Activating Token Index: 468

Text #10

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.8862. Min Act: -0.0001

Data Index: 573994 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1588317 (Python Code)

Max Activating Token Index: 447

Text #12

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1596192 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.8544. Min Act: -0.0000

Data Index: 443259 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.8347. Min Act: -0.0000

Data Index: 305652 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1435457 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1071596 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.8923. Min Act: -0.0000

Data Index: 351401 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.8175. Min Act: -0.0000

Data Index: 443082 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.3201. Min Range: -1.3201

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1017299 (C4 (Web Text))

Max Activating Token Index: 308