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

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

Neuron 1443 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: 3.5097. Min Range: -3.5097

Max Act: 3.5097. Min Act: -0.1700

Data Index: 1225409 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.4627. Min Act: -0.1700

Data Index: 748704 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.4627. Min Act: -0.1700

Data Index: 748892 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.4314. Min Act: -0.1700

Data Index: 1018183 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.4627. Min Act: -0.1700

Data Index: 1043342 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.4157. Min Act: -0.1700

Data Index: 198680 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.4157. Min Act: -0.1700

Data Index: 1199053 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.4000. Min Act: -0.1700

Data Index: 1220645 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3843. Min Act: -0.1700

Data Index: 936080 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3843. Min Act: -0.1700

Data Index: 956383 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3843. Min Act: -0.1700

Data Index: 766715 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3843. Min Act: -0.1700

Data Index: 1295993 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.4000. Min Act: -0.1700

Data Index: 895578 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3686. Min Act: -0.1700

Data Index: 776446 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3686. Min Act: -0.1700

Data Index: 172803 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3686. Min Act: -0.1700

Data Index: 1042453 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3529. Min Act: -0.1700

Data Index: 792061 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3686. Min Act: -0.1700

Data Index: 881626 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3058. Min Act: -0.1700

Data Index: 905941 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 3.5097. Min Range: -3.5097

Max Act: 3.3215. Min Act: -0.1700

Data Index: 503313 (C4 (Web Text))

Max Activating Token Index: 144