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

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

Neuron 464 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: 3.9397. Min Range: -3.9397

Max Act: 3.9397. Min Act: -0.1700

Data Index: 47504 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.9085. Min Act: -0.1700

Data Index: 1036941 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8772. Min Act: -0.1700

Data Index: 1085665 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.9085. Min Act: -0.1700

Data Index: 253917 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 116434 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8772. Min Act: -0.1700

Data Index: 960789 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8772. Min Act: -0.1700

Data Index: 1194659 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8772. Min Act: -0.1700

Data Index: 368066 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 816122 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1256505 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 60815 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1319642 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 456384 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 472085 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 210129 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8772. Min Act: -0.1700

Data Index: 1189273 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1267543 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 857035 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 808684 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8146. Min Act: -0.1700

Data Index: 103625 (C4 (Web Text))

Max Activating Token Index: 932