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

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

Neuron 802 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: 3.4150. Min Range: -3.4150

Max Act: 3.4150. Min Act: -0.1700

Data Index: 162673 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3836. Min Act: -0.1700

Data Index: 360215 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3679. Min Act: -0.1700

Data Index: 568306 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3522. Min Act: -0.1700

Data Index: 161917 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3208. Min Act: -0.1700

Data Index: 1193839 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3679. Min Act: -0.1700

Data Index: 37871 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3365. Min Act: -0.1700

Data Index: 595934 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3365. Min Act: -0.1700

Data Index: 861338 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3208. Min Act: -0.1700

Data Index: 972220 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3051. Min Act: -0.1700

Data Index: 609385 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3208. Min Act: -0.1700

Data Index: 880406 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3051. Min Act: -0.1700

Data Index: 769526 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3051. Min Act: -0.1700

Data Index: 168871 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3208. Min Act: -0.1700

Data Index: 544196 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3051. Min Act: -0.1700

Data Index: 565300 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.2894. Min Act: -0.1700

Data Index: 562947 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3208. Min Act: -0.1700

Data Index: 279850 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3051. Min Act: -0.1700

Data Index: 96538 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.2894. Min Act: -0.1700

Data Index: 1099494 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.2894. Min Act: -0.1700

Data Index: 728782 (C4 (Web Text))

Max Activating Token Index: 501