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

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

Neuron 1530 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: 3.5085. Min Range: -3.5085

Max Act: 3.5085. Min Act: -0.1700

Data Index: 517476 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4458. Min Act: -0.1700

Data Index: 553730 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4771. Min Act: -0.1700

Data Index: 937237 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4771. Min Act: -0.1700

Data Index: 1129518 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4458. Min Act: -0.1700

Data Index: 934564 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.4144. Min Act: -0.1700

Data Index: 619805 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3831. Min Act: -0.1700

Data Index: 1043088 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3517. Min Act: -0.1700

Data Index: 683656 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3831. Min Act: -0.1700

Data Index: 861475 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3203. Min Act: -0.1700

Data Index: 712008 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3203. Min Act: -0.1700

Data Index: 1039581 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3203. Min Act: -0.1700

Data Index: 1308570 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.2889. Min Act: -0.1700

Data Index: 762896 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.2574. Min Act: -0.1700

Data Index: 1104620 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.2260. Min Act: -0.1700

Data Index: 1158026 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.2889. Min Act: -0.1700

Data Index: 1155061 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.3203. Min Act: -0.1700

Data Index: 63321 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.2574. Min Act: -0.1700

Data Index: 116861 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.2260. Min Act: -0.1700

Data Index: 1162295 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 3.5085. Min Range: -3.5085

Max Act: 3.2889. Min Act: -0.1700

Data Index: 1131338 (C4 (Web Text))

Max Activating Token Index: 777