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

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

Neuron 773 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: 3.0362. Min Range: -3.0362

Max Act: 3.0362. Min Act: -0.1700

Data Index: 147742 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 3.0362. Min Range: -3.0362

Max Act: 3.0131. Min Act: -0.1700

Data Index: 407697 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9890. Min Act: -0.1700

Data Index: 1495639 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9707. Min Act: -0.1700

Data Index: 819507 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9772. Min Act: -0.1700

Data Index: 1573855 (Python Code)

Max Activating Token Index: 731

Text #5

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9815. Min Act: -0.1700

Data Index: 1097097 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9677. Min Act: -0.1700

Data Index: 55100 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9519. Min Act: -0.1700

Data Index: 1487618 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9556. Min Act: -0.1700

Data Index: 1565515 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9516. Min Act: -0.1700

Data Index: 1427806 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9407. Min Act: -0.1700

Data Index: 73455 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9178. Min Act: -0.1700

Data Index: 1523124 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9214. Min Act: -0.1700

Data Index: 932258 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9120. Min Act: -0.1700

Data Index: 1289203 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.8884. Min Act: -0.1697

Data Index: 1569936 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.9051. Min Act: -0.1700

Data Index: 1603370 (Python Code)

Max Activating Token Index: 270

Text #16

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.8904. Min Act: -0.1700

Data Index: 1386182 (Python Code)

Max Activating Token Index: 335

Text #17

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.8921. Min Act: -0.1700

Data Index: 1552986 (Python Code)

Max Activating Token Index: 722

Text #18

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.8915. Min Act: -0.1700

Data Index: 1199112 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.0362. Min Range: -3.0362

Max Act: 2.8829. Min Act: -0.1700

Data Index: 1520475 (Python Code)

Max Activating Token Index: 122