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

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

Neuron 1234 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: 4.8400. Min Range: -4.8400

Max Act: 4.8400. Min Act: -0.1700

Data Index: 479090 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8087. Min Act: -0.1700

Data Index: 212362 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8400. Min Act: -0.1700

Data Index: 60191 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8400. Min Act: -0.1700

Data Index: 1120069 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8087. Min Act: -0.1700

Data Index: 291411 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8087. Min Act: -0.1700

Data Index: 126156 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7775. Min Act: -0.1700

Data Index: 191732 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8400. Min Act: -0.1700

Data Index: 937395 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8087. Min Act: -0.1700

Data Index: 875931 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8087. Min Act: -0.1700

Data Index: 156202 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8087. Min Act: -0.1700

Data Index: 1279783 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.8087. Min Act: -0.1700

Data Index: 497202 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7462. Min Act: -0.1700

Data Index: 179669 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7775. Min Act: -0.1700

Data Index: 272595 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7775. Min Act: -0.1700

Data Index: 265032 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7462. Min Act: -0.1700

Data Index: 726296 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7775. Min Act: -0.1700

Data Index: 990049 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7775. Min Act: -0.1700

Data Index: 970039 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7775. Min Act: -0.1700

Data Index: 268545 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 4.8400. Min Range: -4.8400

Max Act: 4.7775. Min Act: -0.1700

Data Index: 885745 (C4 (Web Text))

Max Activating Token Index: 229