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

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

Neuron 123 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.5348. Min Act: -0.1700

Data Index: 62094 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4721. Min Act: -0.1700

Data Index: 530496 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4564. Min Act: -0.1700

Data Index: 664336 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4407. Min Act: -0.1700

Data Index: 172952 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4721. Min Act: -0.1700

Data Index: 964824 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4407. Min Act: -0.1700

Data Index: 482255 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4250. Min Act: -0.1700

Data Index: 1147226 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4564. Min Act: -0.1700

Data Index: 1031750 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4094. Min Act: -0.1700

Data Index: 463852 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4094. Min Act: -0.1700

Data Index: 994061 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3937. Min Act: -0.1700

Data Index: 887759 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4250. Min Act: -0.1700

Data Index: 224699 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4094. Min Act: -0.1700

Data Index: 389109 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4564. Min Act: -0.1700

Data Index: 1008519 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4250. Min Act: -0.1700

Data Index: 915249 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4250. Min Act: -0.1700

Data Index: 950084 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4250. Min Act: -0.1700

Data Index: 782491 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3937. Min Act: -0.1700

Data Index: 112943 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4250. Min Act: -0.1700

Data Index: 438602 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3780. Min Act: -0.1700

Data Index: 582743 (C4 (Web Text))

Max Activating Token Index: 972