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

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

Neuron 1316 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: 5.1210. Min Range: -5.1210

Max Act: 5.1210. Min Act: -0.1700

Data Index: 1042777 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9023. Min Act: -0.1700

Data Index: 980091 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 5.1210. Min Range: -5.1210

Max Act: 5.0273. Min Act: -0.1700

Data Index: 1110454 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 5.1210. Min Range: -5.1210

Max Act: 5.0585. Min Act: -0.1700

Data Index: 1109184 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 5.1210. Min Range: -5.1210

Max Act: 5.0273. Min Act: -0.1700

Data Index: 142172 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 5.1210. Min Range: -5.1210

Max Act: 5.0898. Min Act: -0.1700

Data Index: 751784 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9335. Min Act: -0.1700

Data Index: 560186 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 5.1210. Min Range: -5.1210

Max Act: 5.0585. Min Act: -0.1700

Data Index: 366678 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9960. Min Act: -0.1700

Data Index: 1079072 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 5.1210. Min Range: -5.1210

Max Act: 5.0585. Min Act: -0.1700

Data Index: 1310209 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9960. Min Act: -0.1700

Data Index: 783586 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.8398. Min Act: -0.1700

Data Index: 894378 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9335. Min Act: -0.1700

Data Index: 396073 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9335. Min Act: -0.1700

Data Index: 425680 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 5.1210. Min Range: -5.1210

Max Act: 5.0273. Min Act: -0.1700

Data Index: 715458 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9335. Min Act: -0.1700

Data Index: 278164 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9335. Min Act: -0.1700

Data Index: 134602 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9023. Min Act: -0.1700

Data Index: 185882 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9335. Min Act: -0.1700

Data Index: 432998 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 5.1210. Min Range: -5.1210

Max Act: 4.9023. Min Act: -0.1700

Data Index: 905388 (C4 (Web Text))

Max Activating Token Index: 385