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

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

Neuron 874 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0193. Min Range: -3.0193

Max Act: 3.0193. Min Act: -0.1700

Data Index: 62178 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 3.0193. Min Range: -3.0193

Max Act: 3.0035. Min Act: -0.1700

Data Index: 1334619 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.9719. Min Act: -0.1700

Data Index: 1346596 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.9085. Min Act: -0.1700

Data Index: 117535 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.9244. Min Act: -0.1700

Data Index: 18237 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.9085. Min Act: -0.1700

Data Index: 918931 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8450. Min Act: -0.1700

Data Index: 1188188 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8609. Min Act: -0.1700

Data Index: 755553 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8768. Min Act: -0.1700

Data Index: 954054 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8450. Min Act: -0.1700

Data Index: 348378 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8291. Min Act: -0.1700

Data Index: 748721 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8609. Min Act: -0.1700

Data Index: 671167 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8609. Min Act: -0.1700

Data Index: 1000035 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8768. Min Act: -0.1700

Data Index: 882187 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8450. Min Act: -0.1700

Data Index: 1256789 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8609. Min Act: -0.1700

Data Index: 1103953 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8450. Min Act: -0.1700

Data Index: 1136686 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8291. Min Act: -0.1700

Data Index: 994262 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8291. Min Act: -0.1700

Data Index: 830492 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 3.0193. Min Range: -3.0193

Max Act: 2.8450. Min Act: -0.1700

Data Index: 826535 (C4 (Web Text))

Max Activating Token Index: 741