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

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

Neuron 673 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: 5.9174. Min Range: -5.9174

Max Act: 5.9174. Min Act: -0.1700

Data Index: 476762 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7924. Min Act: -0.1700

Data Index: 475459 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.8237. Min Act: -0.1700

Data Index: 141242 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7924. Min Act: -0.1700

Data Index: 727234 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7924. Min Act: -0.1700

Data Index: 713748 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7612. Min Act: -0.1700

Data Index: 466979 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7612. Min Act: -0.1700

Data Index: 195248 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7924. Min Act: -0.1700

Data Index: 987972 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7924. Min Act: -0.1700

Data Index: 675198 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.6987. Min Act: -0.1700

Data Index: 692374 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7299. Min Act: -0.1700

Data Index: 955563 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7299. Min Act: -0.1700

Data Index: 1248964 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7299. Min Act: -0.1700

Data Index: 813847 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7299. Min Act: -0.1700

Data Index: 6111 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.6987. Min Act: -0.1700

Data Index: 1166411 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.6987. Min Act: -0.1700

Data Index: 998080 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.7299. Min Act: -0.1700

Data Index: 1251048 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.6674. Min Act: -0.1700

Data Index: 1102450 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.6987. Min Act: -0.1700

Data Index: 191606 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 5.9174. Min Range: -5.9174

Max Act: 5.6987. Min Act: -0.1700

Data Index: 1211191 (C4 (Web Text))

Max Activating Token Index: 657