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

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

Neuron 150 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.6396. Min Act: -0.1700

Data Index: 147241 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.6083. Min Act: -0.1700

Data Index: 759358 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.6396. Min Act: -0.1700

Data Index: 757358 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.6083. Min Act: -0.1700

Data Index: 1301227 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5456. Min Act: -0.1700

Data Index: 721014 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5769. Min Act: -0.1700

Data Index: 1079717 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.6083. Min Act: -0.1700

Data Index: 1323065 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5143. Min Act: -0.1700

Data Index: 1350918 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5143. Min Act: -0.1700

Data Index: 1076071 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5143. Min Act: -0.1700

Data Index: 236595 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5143. Min Act: -0.1700

Data Index: 1002413 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5456. Min Act: -0.1700

Data Index: 792348 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5143. Min Act: -0.1700

Data Index: 370257 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.4830. Min Act: -0.1700

Data Index: 890631 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5143. Min Act: -0.1700

Data Index: 257143 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.4203. Min Act: -0.1700

Data Index: 141924 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.4516. Min Act: -0.1700

Data Index: 135587 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.4673. Min Act: -0.1700

Data Index: 692977 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.4830. Min Act: -0.1700

Data Index: 640552 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 3.6396. Min Range: -3.6396

Max Act: 3.5143. Min Act: -0.1700

Data Index: 557094 (C4 (Web Text))

Max Activating Token Index: 705