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

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

Neuron 1923 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.7286. Min Act: -0.1700

Data Index: 346422 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.7286. Min Act: -0.1700

Data Index: 1217053 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.6974. Min Act: -0.1700

Data Index: 496694 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.6349. Min Act: -0.1700

Data Index: 1186578 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.6036. Min Act: -0.1700

Data Index: 374530 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.5724. Min Act: -0.1700

Data Index: 248869 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.5411. Min Act: -0.1700

Data Index: 203625 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.5099. Min Act: -0.1700

Data Index: 1053045 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.5099. Min Act: -0.1700

Data Index: 95566 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.5099. Min Act: -0.1700

Data Index: 332814 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4786. Min Act: -0.1700

Data Index: 327774 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4474. Min Act: -0.1700

Data Index: 127850 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4786. Min Act: -0.1699

Data Index: 140205 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4474. Min Act: -0.1700

Data Index: 1093441 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4474. Min Act: -0.1700

Data Index: 1077588 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.3849. Min Act: -0.1700

Data Index: 949744 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4161. Min Act: -0.1700

Data Index: 577615 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4474. Min Act: -0.1700

Data Index: 869103 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4474. Min Act: -0.1700

Data Index: 632403 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 5.7286. Min Range: -5.7286

Max Act: 5.4161. Min Act: -0.1608

Data Index: 554257 (C4 (Web Text))

Max Activating Token Index: 702