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

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

Neuron 250 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: 3.4190. Min Range: -3.4190

Max Act: 3.4190. Min Act: -0.1700

Data Index: 385140 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.2416. Min Act: -0.1700

Data Index: 838524 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.2428. Min Act: -0.1700

Data Index: 169461 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1812. Min Act: -0.1700

Data Index: 943809 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1102421 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1633. Min Act: -0.1700

Data Index: 410926 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1488. Min Act: -0.1700

Data Index: 307310 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1504. Min Act: -0.1700

Data Index: 167470 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1183. Min Act: -0.1700

Data Index: 1035987 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1375. Min Act: -0.1700

Data Index: 78724 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1206. Min Act: -0.1700

Data Index: 706668 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1136. Min Act: -0.1700

Data Index: 332020 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1057. Min Act: -0.1700

Data Index: 962113 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1145. Min Act: -0.1700

Data Index: 188274 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.0959. Min Act: -0.1700

Data Index: 13968 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.1065. Min Act: -0.1700

Data Index: 638369 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.0805. Min Act: -0.1700

Data Index: 1088619 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.0866. Min Act: -0.1700

Data Index: 172419 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.0776. Min Act: -0.1700

Data Index: 1282717 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.4190. Min Range: -3.4190

Max Act: 3.0859. Min Act: -0.1700

Data Index: 1157942 (C4 (Web Text))

Max Activating Token Index: 854