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

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

Neuron 2906 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1496423 (Python Code)

Max Activating Token Index: 191

Text #1

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1625591 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1602938 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1534620 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4441. Min Act: -0.0001

Data Index: 1602812 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1400725 (Python Code)

Max Activating Token Index: 879

Text #6

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1366199 (Python Code)

Max Activating Token Index: 318

Text #7

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1531984 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1368353 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1433085 (Python Code)

Max Activating Token Index: 436

Text #10

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1641632 (Python Code)

Max Activating Token Index: 516

Text #11

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1510171 (Python Code)

Max Activating Token Index: 679

Text #12

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1490035 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1494311 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1536244 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1460550 (Python Code)

Max Activating Token Index: 646

Text #16

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1616750 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1443203 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1392318 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1627399 (Python Code)

Max Activating Token Index: 569