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

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

Neuron 1183 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.2839. Min Act: -0.1700

Data Index: 1281924 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.2682. Min Act: -0.1700

Data Index: 880211 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.2368. Min Act: -0.1700

Data Index: 821693 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.2053. Min Act: -0.1700

Data Index: 1322640 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.2368. Min Act: -0.1700

Data Index: 893704 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.2053. Min Act: -0.1700

Data Index: 333363 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.2211. Min Act: -0.1700

Data Index: 416978 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1896. Min Act: -0.1700

Data Index: 233935 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1581. Min Act: -0.1700

Data Index: 1181082 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1581. Min Act: -0.1700

Data Index: 218265 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1739. Min Act: -0.1700

Data Index: 380326 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1581. Min Act: -0.1700

Data Index: 423847 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1581. Min Act: -0.1700

Data Index: 323978 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1424. Min Act: -0.1700

Data Index: 791747 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1424. Min Act: -0.1700

Data Index: 476232 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1424. Min Act: -0.1700

Data Index: 937149 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1581. Min Act: -0.1700

Data Index: 137782 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1581. Min Act: -0.1700

Data Index: 1079056 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1424. Min Act: -0.1700

Data Index: 833726 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 3.2839. Min Range: -3.2839

Max Act: 3.1424. Min Act: -0.1700

Data Index: 1096228 (C4 (Web Text))

Max Activating Token Index: 784