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

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

Neuron 5302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0061. Min Range: -7.0061

Max Act: 7.0061. Min Act: -0.0001

Data Index: 1459068 (Python Code)

Max Activating Token Index: 472

Text #1

Max Range: 7.0061. Min Range: -7.0061

Max Act: 6.7999. Min Act: -0.0001

Data Index: 1397518 (Python Code)

Max Activating Token Index: 836

Text #2

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.8077. Min Act: -0.0001

Data Index: 1420149 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.3199. Min Act: -0.0001

Data Index: 1480835 (Python Code)

Max Activating Token Index: 448

Text #4

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.7558. Min Act: -0.0001

Data Index: 1451900 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.6242. Min Act: -0.0001

Data Index: 1385105 (Python Code)

Max Activating Token Index: 231

Text #6

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.4461. Min Act: -0.0001

Data Index: 1543573 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.4344. Min Act: -0.0001

Data Index: 1647367 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.4286. Min Act: -0.0001

Data Index: 1593106 (Python Code)

Max Activating Token Index: 715

Text #9

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.5777. Min Act: -0.0001

Data Index: 1379886 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.4044. Min Act: -0.0001

Data Index: 1419221 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.3035. Min Act: -0.0001

Data Index: 1596994 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.1558. Min Act: -0.0001

Data Index: 1597181 (Python Code)

Max Activating Token Index: 684

Text #13

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.2499. Min Act: -0.0001

Data Index: 1628658 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.0753. Min Act: -0.0001

Data Index: 1537416 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.2358. Min Act: -0.0001

Data Index: 1601022 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.2204. Min Act: -0.0001

Data Index: 1436872 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.2153. Min Act: -0.0001

Data Index: 1596963 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 7.0061. Min Range: -7.0061

Max Act: 4.1482. Min Act: -0.0001

Data Index: 1386511 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 7.0061. Min Range: -7.0061

Max Act: 3.9769. Min Act: -0.0001

Data Index: 1591096 (Python Code)

Max Activating Token Index: 76