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

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

Neuron 1058 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: 4.2953. Min Range: -4.2953

Max Act: 4.2532. Min Act: -0.1700

Data Index: 1019341 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.2953. Min Act: -0.1496

Data Index: 1361808 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.2402. Min Act: -0.1693

Data Index: 834702 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.1797. Min Act: -0.1699

Data Index: 680490 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.1723. Min Act: -0.1691

Data Index: 1203606 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.1982. Min Act: -0.1699

Data Index: 345737 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.1674. Min Act: -0.1700

Data Index: 1288946 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.1317. Min Act: -0.1700

Data Index: 102362 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.1185. Min Act: -0.1700

Data Index: 530462 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.0688. Min Act: -0.1696

Data Index: 1233695 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.0857. Min Act: -0.1700

Data Index: 292286 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.0852. Min Act: -0.1700

Data Index: 1213539 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.0070. Min Act: -0.1699

Data Index: 1634619 (Python Code)

Max Activating Token Index: 719

Text #13

Max Range: 4.2953. Min Range: -4.2953

Max Act: 3.9838. Min Act: -0.1700

Data Index: 1493138 (Python Code)

Max Activating Token Index: 567

Text #14

Max Range: 4.2953. Min Range: -4.2953

Max Act: 3.9881. Min Act: -0.1700

Data Index: 1322708 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 4.2953. Min Range: -4.2953

Max Act: 3.9930. Min Act: -0.1700

Data Index: 1146020 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 4.2953. Min Range: -4.2953

Max Act: 3.9955. Min Act: -0.1700

Data Index: 581262 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.0350. Min Act: -0.1650

Data Index: 588606 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.0195. Min Act: -0.1699

Data Index: 1345821 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 4.2953. Min Range: -4.2953

Max Act: 4.0262. Min Act: -0.1694

Data Index: 213018 (C4 (Web Text))

Max Activating Token Index: 484