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

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

Neuron 514 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.4918. Min Act: -0.1700

Data Index: 247396 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.4918. Min Act: -0.1694

Data Index: 1106083 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.3981. Min Act: -0.1700

Data Index: 369260 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.3981. Min Act: -0.1698

Data Index: 669381 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.2418. Min Act: -0.1700

Data Index: 1354669 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.3043. Min Act: -0.1700

Data Index: 1023905 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.2418. Min Act: -0.1700

Data Index: 249864 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.2731. Min Act: -0.1700

Data Index: 1359145 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.2106. Min Act: -0.1700

Data Index: 580766 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.2106. Min Act: -0.1700

Data Index: 569841 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.2106. Min Act: -0.1700

Data Index: 520848 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1793. Min Act: -0.1700

Data Index: 975736 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1793. Min Act: -0.1700

Data Index: 696548 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1793. Min Act: -0.1700

Data Index: 833295 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1793. Min Act: -0.1700

Data Index: 473825 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1793. Min Act: -0.1700

Data Index: 900950 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1168. Min Act: -0.1700

Data Index: 519624 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1481. Min Act: -0.1700

Data Index: 923107 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1168. Min Act: -0.1700

Data Index: 966162 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 5.4918. Min Range: -5.4918

Max Act: 5.1481. Min Act: -0.1700

Data Index: 447527 (C4 (Web Text))

Max Activating Token Index: 889