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

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

Neuron 3451 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.2512. Min Act: -0.0000

Data Index: 1460613 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0895. Min Act: -0.0000

Data Index: 1530643 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.8445. Min Act: -0.0000

Data Index: 1428397 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.6399. Min Act: -0.0000

Data Index: 1501835 (Python Code)

Max Activating Token Index: 575

Text #4

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.6099. Min Act: -0.0000

Data Index: 1379116 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.5585. Min Act: -0.0000

Data Index: 1493329 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9494. Min Act: -0.0000

Data Index: 1637190 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.6259. Min Act: -0.0000

Data Index: 1604873 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.3162. Min Act: -0.0000

Data Index: 1618152 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.3158. Min Act: -0.0000

Data Index: 1483319 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.2677. Min Act: -0.0000

Data Index: 1642463 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.2457. Min Act: -0.0000

Data Index: 1540677 (Python Code)

Max Activating Token Index: 914

Text #12

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.2430. Min Act: -0.0000

Data Index: 1544971 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.3448. Min Act: -0.0000

Data Index: 1624248 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.3416. Min Act: -0.0000

Data Index: 1461500 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.3201. Min Act: -0.0000

Data Index: 1598707 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.3232. Min Act: -0.0000

Data Index: 1477275 (Python Code)

Max Activating Token Index: 626

Text #17

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.7064. Min Act: -0.0000

Data Index: 1641465 (Python Code)

Max Activating Token Index: 409

Text #18

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.1789. Min Act: -0.0000

Data Index: 1602574 (Python Code)

Max Activating Token Index: 820

Text #19

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.2102. Min Act: -0.0000

Data Index: 1493511 (Python Code)

Max Activating Token Index: 142