Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1309 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.2312. Min Act: -0.1700

Data Index: 1441019 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.1525. Min Act: -0.1700

Data Index: 1640624 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0737. Min Act: -0.1700

Data Index: 320478 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1171951 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.1210. Min Act: -0.1700

Data Index: 1425227 (Python Code)

Max Activating Token Index: 702

Text #5

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.1210. Min Act: -0.1700

Data Index: 726099 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.1053. Min Act: -0.1700

Data Index: 1470485 (Python Code)

Max Activating Token Index: 579

Text #7

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1474112 (Python Code)

Max Activating Token Index: 348

Text #8

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0737. Min Act: -0.1700

Data Index: 1646388 (Python Code)

Max Activating Token Index: 634

Text #9

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1515783 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1623827 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0421. Min Act: -0.1700

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 3.2312. Min Range: -3.2312

Max Act: 2.9789. Min Act: -0.1700

Data Index: 564575 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0579. Min Act: -0.1700

Data Index: 1656133 (Python Code)

Max Activating Token Index: 635

Text #14

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0421. Min Act: -0.1700

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0579. Min Act: -0.1700

Data Index: 779926 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1243613 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0737. Min Act: -0.1700

Data Index: 1593591 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0579. Min Act: -0.1700

Data Index: 337494 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 3.2312. Min Range: -3.2312

Max Act: 3.0579. Min Act: -0.1700

Data Index: 1626293 (Python Code)

Max Activating Token Index: 255