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

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

Neuron 922 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5448. Min Act: -0.1700

Data Index: 183107 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.7010. Min Act: -0.1700

Data Index: 342040 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5916. Min Act: -0.1700

Data Index: 1177873 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5604. Min Act: -0.1700

Data Index: 293462 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5135. Min Act: -0.1700

Data Index: 829916 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5604. Min Act: -0.1700

Data Index: 1180150 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5916. Min Act: -0.1700

Data Index: 702356 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.4666. Min Act: -0.1700

Data Index: 202830 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5135. Min Act: -0.1700

Data Index: 305246 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.5135. Min Act: -0.1700

Data Index: 167329 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3885. Min Act: -0.1700

Data Index: 206256 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.4354. Min Act: -0.1700

Data Index: 716325 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3729. Min Act: -0.1700

Data Index: 811000 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3885. Min Act: -0.1700

Data Index: 1140982 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3573. Min Act: -0.1700

Data Index: 283461 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3260. Min Act: -0.1700

Data Index: 454814 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3729. Min Act: -0.1700

Data Index: 1324818 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3729. Min Act: -0.1700

Data Index: 315459 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.4041. Min Act: -0.1700

Data Index: 263064 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 5.7010. Min Range: -5.7010

Max Act: 5.3573. Min Act: -0.1700

Data Index: 1165285 (C4 (Web Text))

Max Activating Token Index: 958