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

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

Neuron 2332 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1396397 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1524633 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1410232 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1395046 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1501087 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1595815 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1508130 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1363357 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1541057 (Python Code)

Max Activating Token Index: 998

Text #9

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1466023 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1422596 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1421965 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1389354 (Python Code)

Max Activating Token Index: 804

Text #13

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1399701 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1521130 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1642099 (Python Code)

Max Activating Token Index: 298

Text #16

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1446135 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1421862 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1459799 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1448459 (Python Code)

Max Activating Token Index: 967