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

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

Neuron 1404 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5489. Min Act: -0.1700

Data Index: 674226 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5489. Min Act: -0.1700

Data Index: 175549 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5333. Min Act: -0.1700

Data Index: 358525 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5019. Min Act: -0.1700

Data Index: 872913 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5176. Min Act: -0.1700

Data Index: 576978 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5019. Min Act: -0.1700

Data Index: 884457 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5176. Min Act: -0.1700

Data Index: 169764 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5176. Min Act: -0.1700

Data Index: 1322198 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5176. Min Act: -0.1700

Data Index: 206088 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5019. Min Act: -0.1700

Data Index: 79313 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5019. Min Act: -0.1700

Data Index: 650581 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.4863. Min Act: -0.1700

Data Index: 276594 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.4863. Min Act: -0.1700

Data Index: 1152520 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5019. Min Act: -0.1700

Data Index: 650525 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5019. Min Act: -0.1700

Data Index: 159283 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5019. Min Act: -0.1700

Data Index: 328393 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.4863. Min Act: -0.1700

Data Index: 254439 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.4863. Min Act: -0.1700

Data Index: 1233625 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.4863. Min Act: -0.1700

Data Index: 111194 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.5019. Min Act: -0.1700

Data Index: 49856 (C4 (Web Text))

Max Activating Token Index: 671