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

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

Neuron 3471 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6460. Min Range: -2.6460

Max Act: 2.6460. Min Act: 0.0000

Data Index: 1574932 (Python Code)

Max Activating Token Index: 938

Text #1

Max Range: 2.6460. Min Range: -2.6460

Max Act: 2.1255. Min Act: -0.0000

Data Index: 1374696 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.7705. Min Act: -0.0000

Data Index: 1415339 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.8544. Min Act: -0.0000

Data Index: 1461045 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.7857. Min Act: -0.0000

Data Index: 1646221 (Python Code)

Max Activating Token Index: 284

Text #5

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.5804. Min Act: -0.0000

Data Index: 1600788 (Python Code)

Max Activating Token Index: 926

Text #6

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.5583. Min Act: -0.0000

Data Index: 1490413 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1543947 (Python Code)

Max Activating Token Index: 845

Text #8

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1593255 (Python Code)

Max Activating Token Index: 830

Text #9

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.4972. Min Act: -0.0000

Data Index: 1587685 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.5797. Min Act: -0.0000

Data Index: 1544286 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1427207 (Python Code)

Max Activating Token Index: 253

Text #12

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1652272 (Python Code)

Max Activating Token Index: 962

Text #13

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.5583. Min Act: -0.0000

Data Index: 1531339 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1594999 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1429590 (Python Code)

Max Activating Token Index: 202

Text #16

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.3947. Min Act: -0.0000

Data Index: 1382031 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1557463 (Python Code)

Max Activating Token Index: 902

Text #18

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.2670. Min Act: -0.0000

Data Index: 1366403 (Python Code)

Max Activating Token Index: 213

Text #19

Max Range: 2.6460. Min Range: -2.6460

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1404854 (Python Code)

Max Activating Token Index: 382