Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1978 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.2764. Min Act: -0.1700

Data Index: 1082047 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.2450. Min Act: -0.1700

Data Index: 1100371 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.2292. Min Act: -0.1700

Data Index: 1196591 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1978. Min Act: -0.1700

Data Index: 405300 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1663. Min Act: -0.1700

Data Index: 556642 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1348. Min Act: -0.1700

Data Index: 234107 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1190. Min Act: -0.1700

Data Index: 907395 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1348. Min Act: -0.1700

Data Index: 598408 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1033. Min Act: -0.1700

Data Index: 718789 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1033. Min Act: -0.1700

Data Index: 1002817 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0875. Min Act: -0.1700

Data Index: 1031315 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0875. Min Act: -0.1700

Data Index: 1009818 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0875. Min Act: -0.1700

Data Index: 447501 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1033. Min Act: -0.1700

Data Index: 1219697 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0875. Min Act: -0.1700

Data Index: 826712 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0875. Min Act: -0.1700

Data Index: 915993 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0875. Min Act: -0.1700

Data Index: 604427 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0402. Min Act: -0.1700

Data Index: 588803 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0717. Min Act: -0.1700

Data Index: 98880 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.0560. Min Act: -0.1700

Data Index: 742939 (C4 (Web Text))

Max Activating Token Index: 105