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

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

Neuron 1667 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: 3.6483. Min Range: -3.6483

Max Act: 3.6483. Min Act: -0.1700

Data Index: 978206 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.6483. Min Act: -0.1700

Data Index: 757133 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5700. Min Act: -0.1700

Data Index: 1160990 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5857. Min Act: -0.1700

Data Index: 92668 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5700. Min Act: -0.1700

Data Index: 1312495 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5543. Min Act: -0.1700

Data Index: 725691 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5543. Min Act: -0.1700

Data Index: 716536 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5543. Min Act: -0.1700

Data Index: 899430 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5230. Min Act: -0.1700

Data Index: 258454 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5230. Min Act: -0.1700

Data Index: 438234 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5543. Min Act: -0.1700

Data Index: 451213 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5230. Min Act: -0.1700

Data Index: 82547 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5230. Min Act: -0.1700

Data Index: 306805 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.5074. Min Act: -0.1700

Data Index: 8690 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.4917. Min Act: -0.1700

Data Index: 829042 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.4917. Min Act: -0.1700

Data Index: 1192033 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.4447. Min Act: -0.1700

Data Index: 67834 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.4760. Min Act: -0.1700

Data Index: 494226 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.4603. Min Act: -0.1700

Data Index: 339799 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 3.6483. Min Range: -3.6483

Max Act: 3.4447. Min Act: -0.1700

Data Index: 731046 (C4 (Web Text))

Max Activating Token Index: 340