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

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

Neuron 1031 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.7322. Min Act: -0.1700

Data Index: 1026091 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.6383. Min Act: -0.1700

Data Index: 605982 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.6070. Min Act: -0.1700

Data Index: 7821 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5757. Min Act: -0.1700

Data Index: 377964 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5757. Min Act: -0.1700

Data Index: 368456 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.6070. Min Act: -0.1700

Data Index: 1191139 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.6070. Min Act: -0.1700

Data Index: 437580 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5757. Min Act: -0.1700

Data Index: 297039 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.6383. Min Act: -0.1700

Data Index: 134364 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5443. Min Act: -0.1700

Data Index: 10390 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5757. Min Act: -0.1700

Data Index: 17773 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.6070. Min Act: -0.1700

Data Index: 898217 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.6070. Min Act: -0.1700

Data Index: 1012674 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5757. Min Act: -0.1700

Data Index: 484636 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.4660. Min Act: -0.1700

Data Index: 537318 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5130. Min Act: -0.1700

Data Index: 127870 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5443. Min Act: -0.1700

Data Index: 101914 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.4817. Min Act: -0.1700

Data Index: 1316791 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.5130. Min Act: -0.1700

Data Index: 984095 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 3.7322. Min Range: -3.7322

Max Act: 3.4817. Min Act: -0.1700

Data Index: 211082 (C4 (Web Text))

Max Activating Token Index: 956