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

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

Neuron 132 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: 3.7286. Min Range: -3.7286

Max Act: 3.7286. Min Act: -0.1700

Data Index: 724949 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6660. Min Act: -0.1700

Data Index: 682208 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6660. Min Act: -0.1700

Data Index: 648967 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6347. Min Act: -0.1700

Data Index: 421529 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6347. Min Act: -0.1700

Data Index: 739846 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6347. Min Act: -0.1700

Data Index: 404275 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6347. Min Act: -0.1700

Data Index: 243061 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6347. Min Act: -0.1699

Data Index: 926859 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6034. Min Act: -0.1700

Data Index: 647491 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6034. Min Act: -0.1700

Data Index: 1034984 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6347. Min Act: -0.1700

Data Index: 919184 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6034. Min Act: -0.1700

Data Index: 881948 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6034. Min Act: -0.1700

Data Index: 737348 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.6034. Min Act: -0.1700

Data Index: 806641 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.5721. Min Act: -0.1700

Data Index: 1189617 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.5407. Min Act: -0.1700

Data Index: 28037 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.5407. Min Act: -0.1700

Data Index: 749294 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.5407. Min Act: -0.1700

Data Index: 809557 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.5094. Min Act: -0.1700

Data Index: 453060 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 3.7286. Min Range: -3.7286

Max Act: 3.5094. Min Act: -0.1700

Data Index: 31861 (C4 (Web Text))

Max Activating Token Index: 427