Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1766 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.5815. Min Act: -0.1700

Data Index: 569119 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.4191. Min Act: -0.1700

Data Index: 1467371 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.3356. Min Act: -0.1700

Data Index: 237835 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.3249. Min Act: -0.1700

Data Index: 1513149 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.3040. Min Act: -0.1700

Data Index: 1488575 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.3265. Min Act: -0.1700

Data Index: 1431270 (Python Code)

Max Activating Token Index: 990

Text #6

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.3201. Min Act: -0.1700

Data Index: 1404457 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2845. Min Act: -0.1700

Data Index: 624964 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2608. Min Act: -0.1700

Data Index: 1587945 (Python Code)

Max Activating Token Index: 738

Text #9

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2407. Min Act: -0.1700

Data Index: 498892 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2541. Min Act: -0.1700

Data Index: 1403455 (Python Code)

Max Activating Token Index: 644

Text #11

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2567. Min Act: -0.1700

Data Index: 1618321 (Python Code)

Max Activating Token Index: 360

Text #12

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2414. Min Act: -0.1700

Data Index: 1527122 (Python Code)

Max Activating Token Index: 478

Text #13

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2252. Min Act: -0.1700

Data Index: 1620559 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.1997. Min Act: -0.1700

Data Index: 81571 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2105. Min Act: -0.1700

Data Index: 1440516 (Python Code)

Max Activating Token Index: 531

Text #16

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.2155. Min Act: -0.1700

Data Index: 1420604 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.1924. Min Act: -0.1700

Data Index: 1413938 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.1944. Min Act: -0.1700

Data Index: 1632407 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 3.5815. Min Range: -3.5815

Max Act: 3.1940. Min Act: -0.1700

Data Index: 1331238 (C4 (Web Text))

Max Activating Token Index: 226