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

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

Neuron 1751 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: 5.7093. Min Range: -5.7093

Max Act: 5.7093. Min Act: -0.1700

Data Index: 1349765 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.6781. Min Act: -0.1700

Data Index: 289846 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.6468. Min Act: -0.1700

Data Index: 717398 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.6156. Min Act: -0.1700

Data Index: 269305 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.6156. Min Act: -0.1700

Data Index: 1007928 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.6156. Min Act: -0.1700

Data Index: 563116 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.5218. Min Act: -0.1700

Data Index: 814820 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.4906. Min Act: -0.1699

Data Index: 1026665 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3968. Min Act: -0.1700

Data Index: 873777 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.4593. Min Act: -0.1700

Data Index: 141078 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3968. Min Act: -0.1700

Data Index: 59957 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3968. Min Act: -0.1700

Data Index: 471352 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3031. Min Act: -0.1700

Data Index: 808503 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3031. Min Act: -0.1700

Data Index: 486900 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3031. Min Act: -0.1700

Data Index: 1235643 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3031. Min Act: -0.1700

Data Index: 568681 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.2406. Min Act: -0.1700

Data Index: 185941 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.2406. Min Act: -0.1700

Data Index: 1204466 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3031. Min Act: -0.1700

Data Index: 855913 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 5.7093. Min Range: -5.7093

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1040761 (C4 (Web Text))

Max Activating Token Index: 274