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

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

Neuron 1218 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: 3.5062. Min Range: -3.5062

Max Act: 3.5062. Min Act: -0.1700

Data Index: 1139099 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.4435. Min Act: -0.1700

Data Index: 940411 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.4122. Min Act: -0.1700

Data Index: 688954 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3808. Min Act: -0.1700

Data Index: 167691 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.4122. Min Act: -0.1700

Data Index: 988111 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.4122. Min Act: -0.1700

Data Index: 1200030 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3808. Min Act: -0.1700

Data Index: 640603 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3494. Min Act: -0.1700

Data Index: 946892 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3180. Min Act: -0.1700

Data Index: 521615 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.2866. Min Act: -0.1700

Data Index: 1275810 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3494. Min Act: -0.1700

Data Index: 238388 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.2552. Min Act: -0.1700

Data Index: 1159454 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.2866. Min Act: -0.1700

Data Index: 994138 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1015301 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.2552. Min Act: -0.1700

Data Index: 429079 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3180. Min Act: -0.1700

Data Index: 976196 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.2866. Min Act: -0.1700

Data Index: 1113750 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.2866. Min Act: -0.1700

Data Index: 784990 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1040270 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 3.5062. Min Range: -3.5062

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1144154 (C4 (Web Text))

Max Activating Token Index: 489