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

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

Neuron 3404 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: 6.8899. Min Range: -6.8899

Max Act: 6.8899. Min Act: -0.0000

Data Index: 1653094 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.7067. Min Act: -0.0000

Data Index: 1391312 (Python Code)

Max Activating Token Index: 934

Text #2

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.6625. Min Act: -0.0000

Data Index: 1461186 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.5805. Min Act: -0.0000

Data Index: 1415003 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.5230. Min Act: -0.0000

Data Index: 1495388 (Python Code)

Max Activating Token Index: 894

Text #5

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.4926. Min Act: -0.0000

Data Index: 1493301 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.4042. Min Act: -0.0000

Data Index: 1426624 (Python Code)

Max Activating Token Index: 190

Text #7

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.2998. Min Act: -0.0000

Data Index: 1411209 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.2292. Min Act: -0.0000

Data Index: 1387688 (Python Code)

Max Activating Token Index: 917

Text #9

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.2449. Min Act: -0.0000

Data Index: 1626873 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.3844. Min Act: -0.0000

Data Index: 1632189 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.2087. Min Act: -0.0000

Data Index: 1365145 (Python Code)

Max Activating Token Index: 846

Text #12

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.3274. Min Act: -0.0000

Data Index: 1467366 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 6.8899. Min Range: -6.8899

Max Act: 5.9922. Min Act: -0.0000

Data Index: 1546220 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 6.8899. Min Range: -6.8899

Max Act: 5.9976. Min Act: -0.0000

Data Index: 1367606 (Python Code)

Max Activating Token Index: 435

Text #15

Max Range: 6.8899. Min Range: -6.8899

Max Act: 5.9309. Min Act: -0.0000

Data Index: 1486897 (Python Code)

Max Activating Token Index: 744

Text #16

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.3346. Min Act: -0.0000

Data Index: 1361957 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 6.8899. Min Range: -6.8899

Max Act: 5.9143. Min Act: -0.0000

Data Index: 1401955 (Python Code)

Max Activating Token Index: 581

Text #18

Max Range: 6.8899. Min Range: -6.8899

Max Act: 6.1768. Min Act: -0.0000

Data Index: 1591496 (Python Code)

Max Activating Token Index: 447

Text #19

Max Range: 6.8899. Min Range: -6.8899

Max Act: 5.9806. Min Act: -0.0000

Data Index: 1394112 (Python Code)

Max Activating Token Index: 339