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

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

Neuron 1137 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: 3.5261. Min Range: -3.5261

Max Act: 3.5261. Min Act: -0.1700

Data Index: 589552 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.4478. Min Act: -0.1700

Data Index: 94647 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.4478. Min Act: -0.1700

Data Index: 448305 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.4321. Min Act: -0.1700

Data Index: 893625 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.4164. Min Act: -0.1700

Data Index: 788639 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.4007. Min Act: -0.1700

Data Index: 23194 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3851. Min Act: -0.1700

Data Index: 324927 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3537. Min Act: -0.1700

Data Index: 756375 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3694. Min Act: -0.1700

Data Index: 634698 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3380. Min Act: -0.1700

Data Index: 1021576 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3694. Min Act: -0.1700

Data Index: 276876 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3223. Min Act: -0.1700

Data Index: 387996 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3223. Min Act: -0.1700

Data Index: 699873 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3066. Min Act: -0.1700

Data Index: 345386 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3223. Min Act: -0.1700

Data Index: 747709 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3066. Min Act: -0.1700

Data Index: 455747 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3066. Min Act: -0.1700

Data Index: 1036661 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3223. Min Act: -0.1700

Data Index: 953489 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3066. Min Act: -0.1700

Data Index: 1337414 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2909. Min Act: -0.1700

Data Index: 664482 (C4 (Web Text))

Max Activating Token Index: 633