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

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

Neuron 1355 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: 3.1859. Min Range: -3.1859

Max Act: 3.1859. Min Act: -0.1700

Data Index: 447373 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.1466. Min Act: -0.1679

Data Index: 1348103 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.1290. Min Act: -0.1700

Data Index: 1201145 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.1220. Min Act: -0.1700

Data Index: 817963 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0900. Min Act: -0.1700

Data Index: 1132073 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0755. Min Act: -0.1700

Data Index: 951891 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0633. Min Act: -0.1700

Data Index: 246055 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0438. Min Act: -0.1700

Data Index: 1024103 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0506. Min Act: -0.1700

Data Index: 672275 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0301. Min Act: -0.1699

Data Index: 593421 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0321. Min Act: -0.1661

Data Index: 1022123 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0382. Min Act: -0.1699

Data Index: 1142376 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0349. Min Act: -0.1700

Data Index: 535310 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0233. Min Act: -0.1700

Data Index: 442091 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0261. Min Act: -0.1700

Data Index: 1350432 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0165. Min Act: -0.1685

Data Index: 769759 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0183. Min Act: -0.1700

Data Index: 1166747 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0184. Min Act: -0.1700

Data Index: 1066060 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0056. Min Act: -0.1700

Data Index: 536356 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 3.1859. Min Range: -3.1859

Max Act: 3.0089. Min Act: -0.1700

Data Index: 989751 (C4 (Web Text))

Max Activating Token Index: 374