Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 773 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.6489. Min Act: -0.1700

Data Index: 1068479 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4766. Min Act: -0.1700

Data Index: 241331 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4923. Min Act: -0.1700

Data Index: 1028113 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4296. Min Act: -0.1700

Data Index: 221915 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4296. Min Act: -0.1700

Data Index: 625680 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3825. Min Act: -0.1700

Data Index: 65292 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4139. Min Act: -0.1700

Data Index: 1350107 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3982. Min Act: -0.1700

Data Index: 499864 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3668. Min Act: -0.1700

Data Index: 126658 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3825. Min Act: -0.1700

Data Index: 1094022 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4139. Min Act: -0.1700

Data Index: 635604 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3668. Min Act: -0.1700

Data Index: 1024724 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3668. Min Act: -0.1700

Data Index: 300265 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3354. Min Act: -0.1700

Data Index: 1038020 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3197. Min Act: -0.1700

Data Index: 889148 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3511. Min Act: -0.1700

Data Index: 540841 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.2726. Min Act: -0.1700

Data Index: 328225 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3668. Min Act: -0.1700

Data Index: 692297 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3354. Min Act: -0.1700

Data Index: 547135 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.3511. Min Act: -0.1700

Data Index: 1253348 (C4 (Web Text))

Max Activating Token Index: 579