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

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

Neuron 3560 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7756. Min Range: -3.7756

Max Act: 3.7756. Min Act: -0.0000

Data Index: 1625160 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 3.7756. Min Range: -3.7756

Max Act: 3.3618. Min Act: -0.0000

Data Index: 1514700 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 3.7756. Min Range: -3.7756

Max Act: 3.6208. Min Act: -0.0000

Data Index: 1639501 (Python Code)

Max Activating Token Index: 112

Text #3

Max Range: 3.7756. Min Range: -3.7756

Max Act: 3.2536. Min Act: -0.0000

Data Index: 1380449 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 3.7756. Min Range: -3.7756

Max Act: 3.5088. Min Act: -0.0000

Data Index: 1471262 (Python Code)

Max Activating Token Index: 219

Text #5

Max Range: 3.7756. Min Range: -3.7756

Max Act: 3.0765. Min Act: -0.0000

Data Index: 1526124 (Python Code)

Max Activating Token Index: 350

Text #6

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.9001. Min Act: -0.0000

Data Index: 1585704 (Python Code)

Max Activating Token Index: 310

Text #7

Max Range: 3.7756. Min Range: -3.7756

Max Act: 3.3289. Min Act: -0.0000

Data Index: 1544291 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.8580. Min Act: -0.0000

Data Index: 1625023 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.8075. Min Act: -0.0000

Data Index: 1628195 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.8930. Min Act: -0.0000

Data Index: 1388915 (Python Code)

Max Activating Token Index: 650

Text #11

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.5806. Min Act: -0.0000

Data Index: 1583697 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.7155. Min Act: -0.0000

Data Index: 1581722 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.6859. Min Act: -0.0000

Data Index: 1435385 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.5942. Min Act: -0.0000

Data Index: 1400828 (Python Code)

Max Activating Token Index: 269

Text #15

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.4424. Min Act: -0.0000

Data Index: 1508808 (Python Code)

Max Activating Token Index: 348

Text #16

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.5545. Min Act: -0.0000

Data Index: 1498022 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.6369. Min Act: -0.0000

Data Index: 1508170 (Python Code)

Max Activating Token Index: 984

Text #18

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.4816. Min Act: -0.0000

Data Index: 1595109 (Python Code)

Max Activating Token Index: 663

Text #19

Max Range: 3.7756. Min Range: -3.7756

Max Act: 2.4762. Min Act: -0.0000

Data Index: 1594589 (Python Code)

Max Activating Token Index: 837