Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1049 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.1129. Min Act: -0.1700

Data Index: 682725 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0656. Min Act: -0.1700

Data Index: 1091322 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0814. Min Act: -0.1700

Data Index: 254090 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0498. Min Act: -0.1700

Data Index: 1216264 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0498. Min Act: -0.1700

Data Index: 1273257 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0340. Min Act: -0.1700

Data Index: 126016 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0340. Min Act: -0.1700

Data Index: 1219749 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0183. Min Act: -0.1700

Data Index: 614950 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0340. Min Act: -0.1700

Data Index: 364975 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0183. Min Act: -0.1700

Data Index: 969646 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0183. Min Act: -0.1700

Data Index: 166787 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0340. Min Act: -0.1700

Data Index: 40169 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0183. Min Act: -0.1700

Data Index: 1277612 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0024. Min Act: -0.1700

Data Index: 758900 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0024. Min Act: -0.1700

Data Index: 751143 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0024. Min Act: -0.1700

Data Index: 417414 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0024. Min Act: -0.1700

Data Index: 23119 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 3.1129. Min Range: -3.1129

Max Act: 3.0024. Min Act: -0.1700

Data Index: 228074 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 3.1129. Min Range: -3.1129

Max Act: 2.9866. Min Act: -0.1700

Data Index: 1046794 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 3.1129. Min Range: -3.1129

Max Act: 2.9866. Min Act: -0.1700

Data Index: 166085 (C4 (Web Text))

Max Activating Token Index: 21