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

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

Neuron 2028 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: 3.3132. Min Range: -3.3132

Max Act: 3.2818. Min Act: -0.1700

Data Index: 512316 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.3132. Min Act: -0.1700

Data Index: 722422 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2818. Min Act: -0.1700

Data Index: 1148901 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2818. Min Act: -0.1700

Data Index: 1227976 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2504. Min Act: -0.1700

Data Index: 266441 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2661. Min Act: -0.1700

Data Index: 653264 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2504. Min Act: -0.1700

Data Index: 859066 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2504. Min Act: -0.1700

Data Index: 794732 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2818. Min Act: -0.1700

Data Index: 739104 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2346. Min Act: -0.1700

Data Index: 911846 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2346. Min Act: -0.1700

Data Index: 344205 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2504. Min Act: -0.1700

Data Index: 930719 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2346. Min Act: -0.1700

Data Index: 977277 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2346. Min Act: -0.1700

Data Index: 1301141 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2661. Min Act: -0.1700

Data Index: 79405 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2346. Min Act: -0.1700

Data Index: 404134 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2346. Min Act: -0.1700

Data Index: 1062212 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2189. Min Act: -0.1700

Data Index: 822739 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2189. Min Act: -0.1700

Data Index: 123009 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2189. Min Act: -0.1700

Data Index: 246827 (C4 (Web Text))

Max Activating Token Index: 366