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

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

Neuron 1364 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: 3.7167. Min Range: -3.7167

Max Act: 3.7167. Min Act: -0.1700

Data Index: 509189 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.7010. Min Act: -0.1700

Data Index: 782463 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.7010. Min Act: -0.1700

Data Index: 1286187 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6541. Min Act: -0.1700

Data Index: 436548 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6541. Min Act: -0.1700

Data Index: 1354546 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6541. Min Act: -0.1700

Data Index: 1072896 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6384. Min Act: -0.1700

Data Index: 815960 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6384. Min Act: -0.1700

Data Index: 327236 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6228. Min Act: -0.1700

Data Index: 1104194 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6228. Min Act: -0.1700

Data Index: 460585 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6228. Min Act: -0.1700

Data Index: 167101 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6071. Min Act: -0.1700

Data Index: 1002505 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6071. Min Act: -0.1700

Data Index: 93483 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6071. Min Act: -0.1700

Data Index: 1108119 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6071. Min Act: -0.1700

Data Index: 619638 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.6071. Min Act: -0.1700

Data Index: 65310 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.5915. Min Act: -0.1700

Data Index: 384828 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.5602. Min Act: -0.1700

Data Index: 79174 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.5915. Min Act: -0.1700

Data Index: 708979 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 3.7167. Min Range: -3.7167

Max Act: 3.5915. Min Act: -0.1700

Data Index: 666962 (C4 (Web Text))

Max Activating Token Index: 240