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

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

Neuron 4477 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0001. Min Range: -1.0001

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1367286 (Python Code)

Max Activating Token Index: 385

Text #1

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1384976 (Python Code)

Max Activating Token Index: 747

Text #2

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.8545. Min Act: -0.0001

Data Index: 1627954 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1642872 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1504823 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1423793 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6821. Min Act: -0.0000

Data Index: 46823 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1451051 (Python Code)

Max Activating Token Index: 172

Text #8

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1358101 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1363739 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1465338 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1100916 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1015849 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1409419 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.5715. Min Act: -0.0000

Data Index: 406117 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1422954 (Python Code)

Max Activating Token Index: 124

Text #16

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6597. Min Act: -0.0001

Data Index: 1568093 (Python Code)

Max Activating Token Index: 256

Text #17

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1497262 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.6206. Min Act: -0.0000

Data Index: 849541 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.0001. Min Range: -1.0001

Max Act: 0.5970. Min Act: -0.0001

Data Index: 319794 (C4 (Web Text))

Max Activating Token Index: 617