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

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

Neuron 1278 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: 3.3409. Min Range: -3.3409

Max Act: 3.3409. Min Act: -0.1700

Data Index: 193897 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.3095. Min Act: -0.1700

Data Index: 778004 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.2309. Min Act: -0.1700

Data Index: 250652 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.1837. Min Act: -0.1700

Data Index: 1324915 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.1680. Min Act: -0.1700

Data Index: 1559378 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.1523. Min Act: -0.1700

Data Index: 390286 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.1050. Min Act: -0.1700

Data Index: 1193339 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.1208. Min Act: -0.1700

Data Index: 309015 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.0735. Min Act: -0.1700

Data Index: 927285 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.0735. Min Act: -0.1700

Data Index: 1082451 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.0735. Min Act: -0.1700

Data Index: 411309 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.0103. Min Act: -0.1700

Data Index: 1016961 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.0103. Min Act: -0.1700

Data Index: 296520 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.0103. Min Act: -0.1700

Data Index: 461199 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.0419. Min Act: -0.1700

Data Index: 219545 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 3.3409. Min Range: -3.3409

Max Act: 2.9945. Min Act: -0.1700

Data Index: 397766 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 3.3409. Min Range: -3.3409

Max Act: 3.0261. Min Act: -0.1700

Data Index: 996849 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 3.3409. Min Range: -3.3409

Max Act: 2.9787. Min Act: -0.1700

Data Index: 11341 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 3.3409. Min Range: -3.3409

Max Act: 2.9945. Min Act: -0.1700

Data Index: 426138 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 3.3409. Min Range: -3.3409

Max Act: 2.9787. Min Act: -0.1700

Data Index: 139423 (C4 (Web Text))

Max Activating Token Index: 826