Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.6138. Min Act: -0.1700

Data Index: 585580 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.5825. Min Act: -0.1700

Data Index: 692393 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.5042. Min Act: -0.1700

Data Index: 235153 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4885. Min Act: -0.1700

Data Index: 890769 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.5042. Min Act: -0.1700

Data Index: 727239 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4572. Min Act: -0.1700

Data Index: 765680 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4572. Min Act: -0.1700

Data Index: 934926 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4572. Min Act: -0.1700

Data Index: 924563 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4415. Min Act: -0.1700

Data Index: 22490 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4572. Min Act: -0.1700

Data Index: 844686 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4572. Min Act: -0.1700

Data Index: 451942 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4415. Min Act: -0.1700

Data Index: 599917 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4258. Min Act: -0.1700

Data Index: 659215 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4102. Min Act: -0.1700

Data Index: 139528 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.3788. Min Act: -0.1700

Data Index: 293709 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4102. Min Act: -0.1700

Data Index: 850587 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4102. Min Act: -0.1700

Data Index: 989692 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4258. Min Act: -0.1700

Data Index: 999560 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.4258. Min Act: -0.1700

Data Index: 1121265 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 3.6138. Min Range: -3.6138

Max Act: 3.3945. Min Act: -0.1700

Data Index: 632541 (C4 (Web Text))

Max Activating Token Index: 579