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

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

Neuron 139 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: 3.5529. Min Range: -3.5529

Max Act: 3.5529. Min Act: -0.1700

Data Index: 6051 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4902. Min Act: -0.1700

Data Index: 24224 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4588. Min Act: -0.1700

Data Index: 58781 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4902. Min Act: -0.1700

Data Index: 1039072 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4902. Min Act: -0.1700

Data Index: 119012 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.5215. Min Act: -0.1700

Data Index: 790198 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4902. Min Act: -0.1700

Data Index: 670311 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4902. Min Act: -0.1700

Data Index: 123207 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4588. Min Act: -0.1700

Data Index: 1289305 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.3961. Min Act: -0.1700

Data Index: 1006541 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4588. Min Act: -0.1700

Data Index: 8855 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4275. Min Act: -0.1700

Data Index: 101116 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.3961. Min Act: -0.1700

Data Index: 661034 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.3961. Min Act: -0.1700

Data Index: 838551 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4275. Min Act: -0.1700

Data Index: 709233 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4588. Min Act: -0.1700

Data Index: 1121532 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4275. Min Act: -0.1700

Data Index: 582667 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.4275. Min Act: -0.1699

Data Index: 1047959 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.3961. Min Act: -0.1700

Data Index: 646489 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 3.5529. Min Range: -3.5529

Max Act: 3.3961. Min Act: -0.1700

Data Index: 283006 (C4 (Web Text))

Max Activating Token Index: 816