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

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

Neuron 694 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: 3.7508. Min Range: -3.7508

Max Act: 3.7508. Min Act: -0.1700

Data Index: 829472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.6587. Min Act: -0.1700

Data Index: 1562941 (Python Code)

Max Activating Token Index: 1005

Text #2

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5528. Min Act: -0.1699

Data Index: 1545129 (Python Code)

Max Activating Token Index: 449

Text #3

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5501. Min Act: -0.1699

Data Index: 1648690 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5615. Min Act: -0.1297

Data Index: 1489546 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5721. Min Act: -0.1699

Data Index: 1499119 (Python Code)

Max Activating Token Index: 785

Text #6

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5249. Min Act: -0.1635

Data Index: 1337642 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5289. Min Act: -0.1699

Data Index: 1522401 (Python Code)

Max Activating Token Index: 827

Text #8

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5220. Min Act: -0.1649

Data Index: 1382247 (Python Code)

Max Activating Token Index: 833

Text #9

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5290. Min Act: -0.1700

Data Index: 1558685 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5326. Min Act: -0.1694

Data Index: 1509070 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5276. Min Act: -0.1698

Data Index: 1493992 (Python Code)

Max Activating Token Index: 959

Text #12

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5398. Min Act: -0.1700

Data Index: 393655 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5107. Min Act: -0.1546

Data Index: 1449249 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5095. Min Act: -0.1613

Data Index: 1601486 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5085. Min Act: -0.1695

Data Index: 1439706 (Python Code)

Max Activating Token Index: 523

Text #16

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4969. Min Act: -0.1700

Data Index: 1487008 (Python Code)

Max Activating Token Index: 290

Text #17

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4886. Min Act: -0.1654

Data Index: 1599898 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4904. Min Act: -0.1700

Data Index: 1545284 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4854. Min Act: -0.1700

Data Index: 1387211 (Python Code)

Max Activating Token Index: 207