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

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

Neuron 1112 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.6871. Min Act: -0.1700

Data Index: 412378 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.6871. Min Act: -0.1700

Data Index: 133004 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.7184. Min Act: -0.1700

Data Index: 1144067 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.7184. Min Act: -0.1700

Data Index: 398213 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.6871. Min Act: -0.1700

Data Index: 715064 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.6871. Min Act: -0.1700

Data Index: 39893 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.5932. Min Act: -0.1700

Data Index: 314681 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.6558. Min Act: -0.1700

Data Index: 947272 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.7497. Min Act: -0.1700

Data Index: 494769 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.7184. Min Act: -0.1700

Data Index: 1272646 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.5932. Min Act: -0.1700

Data Index: 356327 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.5932. Min Act: -0.1700

Data Index: 1288961 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.4992. Min Act: -0.1700

Data Index: 720362 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.5618. Min Act: -0.1700

Data Index: 1224298 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.4992. Min Act: -0.1700

Data Index: 879456 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.5618. Min Act: -0.1700

Data Index: 251154 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.5618. Min Act: -0.1700

Data Index: 1264207 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.4678. Min Act: -0.1700

Data Index: 1226192 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.5305. Min Act: -0.1700

Data Index: 396462 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 3.7497. Min Range: -3.7497

Max Act: 3.4992. Min Act: -0.1700

Data Index: 1144355 (C4 (Web Text))

Max Activating Token Index: 522