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

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

Neuron 427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.8535. Min Act: -0.1700

Data Index: 666434 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.7285. Min Act: -0.1700

Data Index: 169726 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.6660. Min Act: -0.1700

Data Index: 619274 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.6660. Min Act: -0.1700

Data Index: 103299 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.6660. Min Act: -0.1700

Data Index: 848234 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.6035. Min Act: -0.1700

Data Index: 42343 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.6035. Min Act: -0.1700

Data Index: 1267745 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.5410. Min Act: -0.1700

Data Index: 89184 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.6035. Min Act: -0.1700

Data Index: 394254 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.6035. Min Act: -0.1700

Data Index: 1056065 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.5410. Min Act: -0.1700

Data Index: 1237194 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.3535. Min Act: -0.1700

Data Index: 726813 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.4160. Min Act: -0.1700

Data Index: 652455 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.4785. Min Act: -0.1700

Data Index: 785985 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.4160. Min Act: -0.1700

Data Index: 244873 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.2910. Min Act: -0.1700

Data Index: 1238674 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.4160. Min Act: -0.1700

Data Index: 1202003 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.3535. Min Act: -0.1700

Data Index: 112868 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.3535. Min Act: -0.1700

Data Index: 100346 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 7.8535. Min Range: -7.8535

Max Act: 7.3535. Min Act: -0.1700

Data Index: 993602 (C4 (Web Text))

Max Activating Token Index: 400