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

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

Neuron 527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.2193. Min Act: -0.1700

Data Index: 753791 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1721. Min Act: -0.1700

Data Index: 1303947 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1564. Min Act: -0.1700

Data Index: 1154993 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1249. Min Act: -0.1700

Data Index: 421596 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1406. Min Act: -0.1700

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1564. Min Act: -0.1700

Data Index: 788145 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1564. Min Act: -0.1700

Data Index: 443786 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1249. Min Act: -0.1700

Data Index: 354708 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1406. Min Act: -0.1700

Data Index: 789217 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1091. Min Act: -0.1700

Data Index: 555001 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.1249. Min Act: -0.1700

Data Index: 718736 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0618. Min Act: -0.1700

Data Index: 1186023 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0618. Min Act: -0.1700

Data Index: 436711 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0618. Min Act: -0.1700

Data Index: 98199 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0302. Min Act: -0.1700

Data Index: 1136973 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0144. Min Act: -0.1700

Data Index: 925039 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0460. Min Act: -0.1700

Data Index: 1199783 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0302. Min Act: -0.1700

Data Index: 678246 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0776. Min Act: -0.1700

Data Index: 746187 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 3.2193. Min Range: -3.2193

Max Act: 3.0618. Min Act: -0.1700

Data Index: 1119851 (C4 (Web Text))

Max Activating Token Index: 701