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

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

Neuron 2513 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1638236 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1512391 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1497560 (Python Code)

Max Activating Token Index: 439

Text #3

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1554141 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1539897 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1453149 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1504717 (Python Code)

Max Activating Token Index: 220

Text #7

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1451192 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1506146 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1565478 (Python Code)

Max Activating Token Index: 669

Text #10

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1517037 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1510165 (Python Code)

Max Activating Token Index: 218

Text #12

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1623687 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1400041 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1415009 (Python Code)

Max Activating Token Index: 816

Text #15

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1541241 (Python Code)

Max Activating Token Index: 1012

Text #16

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1387911 (Python Code)

Max Activating Token Index: 166

Text #17

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1540245 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1432074 (Python Code)

Max Activating Token Index: 380

Text #19

Max Range: 0.6702. Min Range: -0.6702

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1383171 (Python Code)

Max Activating Token Index: 211