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

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

Neuron 1078 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: 3.9431. Min Range: -3.9431

Max Act: 3.9431. Min Act: -0.1700

Data Index: 694383 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.9431. Min Act: -0.1700

Data Index: 978156 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.8180. Min Act: -0.1700

Data Index: 144463 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.8180. Min Act: -0.1700

Data Index: 16043 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.7554. Min Act: -0.1700

Data Index: 868034 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.7554. Min Act: -0.1700

Data Index: 480103 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.7242. Min Act: -0.1700

Data Index: 110973 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.6929. Min Act: -0.1700

Data Index: 1310003 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.6616. Min Act: -0.1700

Data Index: 274317 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.6929. Min Act: -0.1700

Data Index: 385867 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.6616. Min Act: -0.1700

Data Index: 1044441 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.6616. Min Act: -0.1700

Data Index: 1112202 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.6303. Min Act: -0.1700

Data Index: 816374 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.5989. Min Act: -0.1700

Data Index: 507288 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.6303. Min Act: -0.1700

Data Index: 1052167 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.6303. Min Act: -0.1700

Data Index: 580998 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.5676. Min Act: -0.1700

Data Index: 1265638 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.5989. Min Act: -0.1700

Data Index: 141847 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.5989. Min Act: -0.1700

Data Index: 1023743 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 3.9431. Min Range: -3.9431

Max Act: 3.5989. Min Act: -0.1700

Data Index: 1189427 (C4 (Web Text))

Max Activating Token Index: 216