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

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

Neuron 594 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: 5.2140. Min Range: -5.2140

Max Act: 5.2140. Min Act: -0.1700

Data Index: 182754 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 5.2140. Min Range: -5.2140

Max Act: 5.1202. Min Act: -0.1700

Data Index: 1219839 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 5.2140. Min Range: -5.2140

Max Act: 5.1827. Min Act: -0.1700

Data Index: 49406 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 5.2140. Min Range: -5.2140

Max Act: 5.0890. Min Act: -0.1700

Data Index: 481703 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.9952. Min Act: -0.1700

Data Index: 376448 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.9640. Min Act: -0.1700

Data Index: 386906 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.9952. Min Act: -0.1700

Data Index: 716584 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.9952. Min Act: -0.1700

Data Index: 1141305 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.9015. Min Act: -0.1700

Data Index: 743814 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.8077. Min Act: -0.1700

Data Index: 100410 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.8390. Min Act: -0.1700

Data Index: 1212741 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.8390. Min Act: -0.1700

Data Index: 774086 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.8077. Min Act: -0.1700

Data Index: 1017488 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.8077. Min Act: -0.1700

Data Index: 1266168 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.7140. Min Act: -0.1700

Data Index: 954870 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.7765. Min Act: -0.1700

Data Index: 129288 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.7765. Min Act: -0.1700

Data Index: 836055 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.7765. Min Act: -0.1700

Data Index: 1120157 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.7140. Min Act: -0.1700

Data Index: 667554 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 5.2140. Min Range: -5.2140

Max Act: 4.7140. Min Act: -0.1700

Data Index: 553966 (C4 (Web Text))

Max Activating Token Index: 828