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

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

Neuron 40 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: 4.3913. Min Range: -4.3913

Max Act: 4.3913. Min Act: -0.1670

Data Index: 536222 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.2712. Min Act: -0.1698

Data Index: 1121212 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.3060. Min Act: -0.1700

Data Index: 925396 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.2381. Min Act: -0.1700

Data Index: 403760 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.1329. Min Act: -0.1670

Data Index: 1160117 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.1370. Min Act: -0.1700

Data Index: 862672 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0532. Min Act: -0.1663

Data Index: 1376597 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0431. Min Act: -0.1700

Data Index: 597597 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0389. Min Act: -0.1700

Data Index: 1339789 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0231. Min Act: -0.1700

Data Index: 604570 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0376. Min Act: -0.1700

Data Index: 1469664 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9873. Min Act: -0.1700

Data Index: 767132 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9869. Min Act: -0.1697

Data Index: 590340 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0048. Min Act: -0.1699

Data Index: 1321963 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9475. Min Act: -0.1700

Data Index: 1243546 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9271. Min Act: -0.1700

Data Index: 998406 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9522. Min Act: -0.1700

Data Index: 147438 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9479. Min Act: -0.1699

Data Index: 1417513 (Python Code)

Max Activating Token Index: 580

Text #18

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9073. Min Act: -0.1684

Data Index: 1348540 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.8916. Min Act: -0.1699

Data Index: 1409607 (Python Code)

Max Activating Token Index: 1019