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

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

Neuron 1089 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: 4.1360. Min Range: -4.1360

Max Act: 4.1360. Min Act: -0.1700

Data Index: 1394523 (Python Code)

Max Activating Token Index: 831

Text #1

Max Range: 4.1360. Min Range: -4.1360

Max Act: 4.0636. Min Act: -0.1700

Data Index: 1571212 (Python Code)

Max Activating Token Index: 821

Text #2

Max Range: 4.1360. Min Range: -4.1360

Max Act: 4.0304. Min Act: -0.1700

Data Index: 1479770 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.9518. Min Act: -0.1700

Data Index: 1373219 (Python Code)

Max Activating Token Index: 359

Text #4

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.9567. Min Act: -0.1700

Data Index: 1361988 (Python Code)

Max Activating Token Index: 634

Text #5

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.9317. Min Act: -0.1700

Data Index: 1605966 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.9382. Min Act: -0.1700

Data Index: 1392406 (Python Code)

Max Activating Token Index: 860

Text #7

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8946. Min Act: -0.1700

Data Index: 1464935 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8953. Min Act: -0.1700

Data Index: 1465949 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.9075. Min Act: -0.1700

Data Index: 1454654 (Python Code)

Max Activating Token Index: 839

Text #10

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8937. Min Act: -0.1700

Data Index: 1410921 (Python Code)

Max Activating Token Index: 763

Text #11

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8751. Min Act: -0.1700

Data Index: 1559649 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8552. Min Act: -0.1700

Data Index: 1608169 (Python Code)

Max Activating Token Index: 549

Text #13

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8572. Min Act: -0.1700

Data Index: 1578117 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8452. Min Act: -0.1700

Data Index: 1564150 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8208. Min Act: -0.1700

Data Index: 1605677 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8191. Min Act: -0.1700

Data Index: 1431451 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1630711 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.8027. Min Act: -0.1700

Data Index: 1640121 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 4.1360. Min Range: -4.1360

Max Act: 3.7770. Min Act: -0.1700

Data Index: 1460433 (Python Code)

Max Activating Token Index: 681