Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 102 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0302. Min Range: -4.0302

Max Act: 4.0302. Min Act: -0.1700

Data Index: 256257 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.9051. Min Act: -0.1700

Data Index: 105950 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.8738. Min Act: -0.1700

Data Index: 318862 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.8582. Min Act: -0.1700

Data Index: 695578 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.8582. Min Act: -0.1700

Data Index: 133990 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.8269. Min Act: -0.1700

Data Index: 242956 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.8113. Min Act: -0.1700

Data Index: 1284549 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7956. Min Act: -0.1700

Data Index: 1329529 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7643. Min Act: -0.1700

Data Index: 176221 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7487. Min Act: -0.1700

Data Index: 201913 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7800. Min Act: -0.1700

Data Index: 228921 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7331. Min Act: -0.1700

Data Index: 394925 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7174. Min Act: -0.1700

Data Index: 1181868 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7018. Min Act: -0.1700

Data Index: 16016 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7174. Min Act: -0.1699

Data Index: 332338 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7018. Min Act: -0.1700

Data Index: 1031306 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.6392. Min Act: -0.1700

Data Index: 380648 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.6392. Min Act: -0.1700

Data Index: 139373 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.7018. Min Act: -0.1700

Data Index: 1263048 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 4.0302. Min Range: -4.0302

Max Act: 3.6705. Min Act: -0.1700

Data Index: 1265698 (C4 (Web Text))

Max Activating Token Index: 828