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

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

Neuron 906 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: 5.3233. Min Range: -5.3233

Max Act: 5.3233. Min Act: -0.1700

Data Index: 1310361 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.2921. Min Act: -0.1700

Data Index: 46467 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.2452. Min Act: -0.1700

Data Index: 1154104 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.2140. Min Act: -0.1700

Data Index: 603419 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1983. Min Act: -0.1700

Data Index: 999518 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1358. Min Act: -0.1700

Data Index: 1213814 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1671. Min Act: -0.1700

Data Index: 1224623 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1515. Min Act: -0.1700

Data Index: 1239031 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1671. Min Act: -0.1700

Data Index: 687731 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0890. Min Act: -0.1700

Data Index: 442836 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0733. Min Act: -0.1700

Data Index: 575971 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0733. Min Act: -0.1700

Data Index: 304432 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.1202. Min Act: -0.1700

Data Index: 1071806 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0890. Min Act: -0.1700

Data Index: 913400 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0577. Min Act: -0.1700

Data Index: 677544 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0265. Min Act: -0.1700

Data Index: 722312 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0890. Min Act: -0.1700

Data Index: 180552 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0577. Min Act: -0.1700

Data Index: 1322425 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0108. Min Act: -0.1700

Data Index: 871504 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 5.3233. Min Range: -5.3233

Max Act: 5.0265. Min Act: -0.1700

Data Index: 1016297 (C4 (Web Text))

Max Activating Token Index: 849