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

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

Neuron 636 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: 3.5598. Min Range: -3.5598

Max Act: 3.5598. Min Act: -0.1700

Data Index: 523918 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.5285. Min Act: -0.1700

Data Index: 446716 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.5285. Min Act: -0.1700

Data Index: 651793 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.5129. Min Act: -0.1700

Data Index: 971011 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4972. Min Act: -0.1700

Data Index: 1309904 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4815. Min Act: -0.1700

Data Index: 204685 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4658. Min Act: -0.1700

Data Index: 1291008 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4502. Min Act: -0.1700

Data Index: 1283178 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4188. Min Act: -0.1700

Data Index: 1353590 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.3874. Min Act: -0.1700

Data Index: 980664 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4188. Min Act: -0.1700

Data Index: 882799 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4345. Min Act: -0.1700

Data Index: 266246 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4031. Min Act: -0.1700

Data Index: 656402 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4031. Min Act: -0.1700

Data Index: 115485 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4031. Min Act: -0.1700

Data Index: 1128303 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4188. Min Act: -0.1700

Data Index: 1339261 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.3561. Min Act: -0.1700

Data Index: 1091366 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.3874. Min Act: -0.1700

Data Index: 1103714 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.3561. Min Act: -0.1700

Data Index: 969602 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 3.5598. Min Range: -3.5598

Max Act: 3.4031. Min Act: -0.1700

Data Index: 21884 (C4 (Web Text))

Max Activating Token Index: 359