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

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

Neuron 1765 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: 3.3610. Min Range: -3.3610

Max Act: 3.3610. Min Act: -0.1700

Data Index: 934114 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.3296. Min Act: -0.1700

Data Index: 746808 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.2982. Min Act: -0.1700

Data Index: 944321 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.2825. Min Act: -0.1700

Data Index: 1314498 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.2668. Min Act: -0.1700

Data Index: 638028 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.2354. Min Act: -0.1700

Data Index: 1216184 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.2196. Min Act: -0.1700

Data Index: 1317543 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.2039. Min Act: -0.1700

Data Index: 408522 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1882. Min Act: -0.1700

Data Index: 1354121 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1567. Min Act: -0.1700

Data Index: 720543 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1882. Min Act: -0.1700

Data Index: 181222 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1882. Min Act: -0.1700

Data Index: 421378 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1882. Min Act: -0.1700

Data Index: 198772 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1724. Min Act: -0.1700

Data Index: 1010979 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1409. Min Act: -0.1700

Data Index: 1100368 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1409. Min Act: -0.1700

Data Index: 121001 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1409. Min Act: -0.1700

Data Index: 89213 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1252. Min Act: -0.1700

Data Index: 1147257 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1409. Min Act: -0.1700

Data Index: 947801 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 3.3610. Min Range: -3.3610

Max Act: 3.1094. Min Act: -0.1700

Data Index: 101189 (C4 (Web Text))

Max Activating Token Index: 141