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

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

Neuron 925 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1557287 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2621. Min Act: -0.0001

Data Index: 1445544 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1640206 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1572884 (Python Code)

Max Activating Token Index: 69

Text #4

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1576950 (Python Code)

Max Activating Token Index: 635

Text #5

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1410999 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2237. Min Act: -0.0002

Data Index: 1587405 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2193. Min Act: -0.0001

Data Index: 1480275 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1576393 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2062. Min Act: -0.0001

Data Index: 1526023 (Python Code)

Max Activating Token Index: 151

Text #10

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1611071 (Python Code)

Max Activating Token Index: 346

Text #11

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1375948 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1561091 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2056. Min Act: -0.0002

Data Index: 1654187 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2065. Min Act: -0.0001

Data Index: 1546370 (Python Code)

Max Activating Token Index: 507

Text #15

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2014. Min Act: -0.0001

Data Index: 1533340 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2058. Min Act: -0.0002

Data Index: 1473523 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2005. Min Act: -0.0002

Data Index: 1407573 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1530656 (Python Code)

Max Activating Token Index: 738

Text #19

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1447998 (Python Code)

Max Activating Token Index: 26