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

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

Neuron 1364 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: 3.3182. Min Range: -3.3182

Max Act: 3.3182. Min Act: -0.1700

Data Index: 191935 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.3182. Min Act: -0.1700

Data Index: 326771 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.2554. Min Act: -0.1700

Data Index: 144622 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.2240. Min Act: -0.1700

Data Index: 963685 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.2240. Min Act: -0.1700

Data Index: 1026460 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.2240. Min Act: -0.1700

Data Index: 695419 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1925. Min Act: -0.1700

Data Index: 1243358 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.2554. Min Act: -0.1700

Data Index: 482152 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1925. Min Act: -0.1700

Data Index: 1279102 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1925. Min Act: -0.1700

Data Index: 1286908 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1925. Min Act: -0.1700

Data Index: 750961 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1925. Min Act: -0.1700

Data Index: 1094312 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1610. Min Act: -0.1700

Data Index: 992869 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1295. Min Act: -0.1700

Data Index: 619708 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1610. Min Act: -0.1700

Data Index: 315993 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1610. Min Act: -0.1700

Data Index: 807089 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.0980. Min Act: -0.1700

Data Index: 343635 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1295. Min Act: -0.1700

Data Index: 711194 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1295. Min Act: -0.1700

Data Index: 889058 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.0980. Min Act: -0.1700

Data Index: 825990 (C4 (Web Text))

Max Activating Token Index: 89