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

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

Neuron 217 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: 3.9114. Min Range: -3.9114

Max Act: 3.9114. Min Act: -0.1700

Data Index: 892708 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.9114. Min Act: -0.1700

Data Index: 26979 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.8801. Min Act: -0.1700

Data Index: 1182180 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7863. Min Act: -0.1700

Data Index: 560628 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.8176. Min Act: -0.1700

Data Index: 1084544 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7863. Min Act: -0.1700

Data Index: 251336 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.8176. Min Act: -0.1700

Data Index: 826868 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 1272364 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 1138839 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 806744 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7863. Min Act: -0.1700

Data Index: 1029399 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.8176. Min Act: -0.1700

Data Index: 720449 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.6924. Min Act: -0.1700

Data Index: 867358 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7863. Min Act: -0.1700

Data Index: 560368 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 1177616 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 1001233 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 23475 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 628218 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 509408 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 3.9114. Min Range: -3.9114

Max Act: 3.7550. Min Act: -0.1700

Data Index: 26351 (C4 (Web Text))

Max Activating Token Index: 427