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

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

Neuron 1029 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: 5.6179. Min Range: -5.6179

Max Act: 5.6179. Min Act: -0.1700

Data Index: 1021449 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.5554. Min Act: -0.1700

Data Index: 606897 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.5241. Min Act: -0.1700

Data Index: 697650 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.4304. Min Act: -0.1700

Data Index: 853482 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.4304. Min Act: -0.1700

Data Index: 673189 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.4616. Min Act: -0.1700

Data Index: 594757 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.5554. Min Act: -0.1700

Data Index: 420297 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3679. Min Act: -0.1700

Data Index: 1355191 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3991. Min Act: -0.1700

Data Index: 65820 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3366. Min Act: -0.1700

Data Index: 2112 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3679. Min Act: -0.1700

Data Index: 1321629 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3366. Min Act: -0.1700

Data Index: 1142280 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3366. Min Act: -0.1700

Data Index: 607429 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.2429. Min Act: -0.1700

Data Index: 875196 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3366. Min Act: -0.1700

Data Index: 991449 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3366. Min Act: -0.1700

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3366. Min Act: -0.1700

Data Index: 246536 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3054. Min Act: -0.1700

Data Index: 408989 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.3054. Min Act: -0.1700

Data Index: 612850 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 5.6179. Min Range: -5.6179

Max Act: 5.2429. Min Act: -0.1700

Data Index: 837170 (C4 (Web Text))

Max Activating Token Index: 850