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

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

Neuron 1445 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: 3.4784. Min Range: -3.4784

Max Act: 3.4784. Min Act: -0.1700

Data Index: 1491737 (Python Code)

Max Activating Token Index: 842

Text #1

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.4268. Min Act: -0.1700

Data Index: 1427290 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3876. Min Act: -0.1700

Data Index: 1450634 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3874. Min Act: -0.1700

Data Index: 1433804 (Python Code)

Max Activating Token Index: 685

Text #4

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3865. Min Act: -0.1700

Data Index: 1398917 (Python Code)

Max Activating Token Index: 894

Text #5

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3567. Min Act: -0.1700

Data Index: 520151 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3710. Min Act: -0.1700

Data Index: 1442706 (Python Code)

Max Activating Token Index: 697

Text #7

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3784. Min Act: -0.1699

Data Index: 1540454 (Python Code)

Max Activating Token Index: 372

Text #8

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3268. Min Act: -0.1700

Data Index: 5360 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3166. Min Act: -0.1700

Data Index: 1632570 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3246. Min Act: -0.1700

Data Index: 1526193 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1402779 (Python Code)

Max Activating Token Index: 192

Text #12

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3146. Min Act: -0.1700

Data Index: 1471674 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2964. Min Act: -0.1700

Data Index: 1560928 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2895. Min Act: -0.1699

Data Index: 1404487 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2933. Min Act: -0.1700

Data Index: 27205 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3002. Min Act: -0.1700

Data Index: 759524 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2823. Min Act: -0.1700

Data Index: 188422 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2840. Min Act: -0.1700

Data Index: 1409652 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2628. Min Act: -0.1700

Data Index: 1419611 (Python Code)

Max Activating Token Index: 1012