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

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

Neuron 93 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: 3.4906. Min Range: -3.4906

Max Act: 3.4906. Min Act: -0.1700

Data Index: 301758 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.4749. Min Act: -0.1700

Data Index: 244080 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.4436. Min Act: -0.1700

Data Index: 980689 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.4436. Min Act: -0.1700

Data Index: 731536 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.4749. Min Act: -0.1700

Data Index: 222247 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.4122. Min Act: -0.1700

Data Index: 1000428 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.4122. Min Act: -0.1700

Data Index: 620299 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.4122. Min Act: -0.1700

Data Index: 1117904 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3965. Min Act: -0.1700

Data Index: 1359378 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3965. Min Act: -0.1700

Data Index: 197831 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3808. Min Act: -0.1700

Data Index: 679075 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3651. Min Act: -0.1700

Data Index: 854708 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3808. Min Act: -0.1700

Data Index: 1355121 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3965. Min Act: -0.1700

Data Index: 442237 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3651. Min Act: -0.1700

Data Index: 877654 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3965. Min Act: -0.1700

Data Index: 603543 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3808. Min Act: -0.1700

Data Index: 215720 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3808. Min Act: -0.1700

Data Index: 777755 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3808. Min Act: -0.1700

Data Index: 743683 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 3.4906. Min Range: -3.4906

Max Act: 3.3651. Min Act: -0.1700

Data Index: 715412 (C4 (Web Text))

Max Activating Token Index: 759