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

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

Neuron 1311 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: 3.3903. Min Range: -3.3903

Max Act: 3.3903. Min Act: -0.0825

Data Index: 80824 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3876. Min Act: -0.1700

Data Index: 1509210 (Python Code)

Max Activating Token Index: 469

Text #2

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3805. Min Act: -0.1543

Data Index: 868999 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3778. Min Act: -0.1699

Data Index: 1190985 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3503. Min Act: -0.1700

Data Index: 438973 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3693. Min Act: -0.1699

Data Index: 1539745 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3589. Min Act: -0.0589

Data Index: 1291281 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3416. Min Act: -0.1699

Data Index: 873397 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3351. Min Act: -0.1700

Data Index: 655784 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3256. Min Act: -0.1699

Data Index: 295870 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3055. Min Act: -0.1700

Data Index: 1261276 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3206. Min Act: -0.1700

Data Index: 486037 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3151. Min Act: -0.1700

Data Index: 689653 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.3057. Min Act: -0.1700

Data Index: 934230 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.2975. Min Act: -0.1700

Data Index: 141332 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.2508. Min Act: -0.1700

Data Index: 910888 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.2659. Min Act: -0.1699

Data Index: 1292884 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.2575. Min Act: -0.1700

Data Index: 1489844 (Python Code)

Max Activating Token Index: 590

Text #18

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.2590. Min Act: -0.1700

Data Index: 349224 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 3.3903. Min Range: -3.3903

Max Act: 3.2463. Min Act: -0.1700

Data Index: 225380 (C4 (Web Text))

Max Activating Token Index: 373