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

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

Neuron 2031 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1469. Min Range: -7.1469

Max Act: 7.1469. Min Act: -0.1700

Data Index: 1224431 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 7.1469. Min Range: -7.1469

Max Act: 7.0844. Min Act: -0.1700

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.8969. Min Act: -0.1700

Data Index: 963567 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.8031. Min Act: -0.1700

Data Index: 583796 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.7094. Min Act: -0.1700

Data Index: 291359 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.7406. Min Act: -0.1700

Data Index: 1213427 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.8031. Min Act: -0.1700

Data Index: 82678 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.6156. Min Act: -0.1700

Data Index: 412928 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.7094. Min Act: -0.1700

Data Index: 663200 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.5844. Min Act: -0.1700

Data Index: 780709 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.4594. Min Act: -0.1700

Data Index: 1082564 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.4281. Min Act: -0.1700

Data Index: 290388 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.4906. Min Act: -0.1700

Data Index: 1224835 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.4281. Min Act: -0.1700

Data Index: 32637 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.4594. Min Act: -0.1700

Data Index: 386437 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.4281. Min Act: -0.1700

Data Index: 512348 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.3344. Min Act: -0.1700

Data Index: 163781 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.3656. Min Act: -0.1700

Data Index: 1184486 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.3656. Min Act: -0.1700

Data Index: 583817 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 7.1469. Min Range: -7.1469

Max Act: 6.2094. Min Act: -0.1700

Data Index: 521263 (C4 (Web Text))

Max Activating Token Index: 918