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

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

Neuron 1484 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.5002. Min Act: -0.1700

Data Index: 1167710 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.4688. Min Act: -0.1700

Data Index: 1321630 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.4375. Min Act: -0.1700

Data Index: 520509 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.3591. Min Act: -0.1700

Data Index: 449185 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.3434. Min Act: -0.1700

Data Index: 18526 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.3434. Min Act: -0.1700

Data Index: 964198 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2963. Min Act: -0.1700

Data Index: 226148 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2963. Min Act: -0.1700

Data Index: 599604 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2963. Min Act: -0.1700

Data Index: 107284 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2963. Min Act: -0.1700

Data Index: 1317123 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2491. Min Act: -0.1700

Data Index: 792669 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2805. Min Act: -0.1700

Data Index: 297251 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2648. Min Act: -0.1700

Data Index: 369623 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2648. Min Act: -0.1700

Data Index: 996247 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2491. Min Act: -0.1700

Data Index: 392697 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2491. Min Act: -0.1700

Data Index: 935471 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2648. Min Act: -0.1700

Data Index: 661960 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2334. Min Act: -0.1700

Data Index: 1180169 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2491. Min Act: -0.1700

Data Index: 296969 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 3.5002. Min Range: -3.5002

Max Act: 3.2491. Min Act: -0.1700

Data Index: 200853 (C4 (Web Text))

Max Activating Token Index: 324