Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 113 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.6781. Min Act: -0.1700

Data Index: 608624 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.6468. Min Act: -0.1700

Data Index: 552901 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.4902. Min Act: -0.1700

Data Index: 150509 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.4589. Min Act: -0.1700

Data Index: 332948 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.4589. Min Act: -0.1700

Data Index: 860652 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.4589. Min Act: -0.1700

Data Index: 1084268 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.4275. Min Act: -0.1700

Data Index: 347287 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.4589. Min Act: -0.1700

Data Index: 187932 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.4275. Min Act: -0.1700

Data Index: 775865 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3962. Min Act: -0.1700

Data Index: 277003 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.4275. Min Act: -0.1700

Data Index: 1319025 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3962. Min Act: -0.1700

Data Index: 1189401 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3648. Min Act: -0.1700

Data Index: 593521 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3648. Min Act: -0.1700

Data Index: 188649 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3648. Min Act: -0.1700

Data Index: 963500 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.2706. Min Act: -0.1700

Data Index: 1349324 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3648. Min Act: -0.1700

Data Index: 1295053 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3648. Min Act: -0.1700

Data Index: 379832 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3020. Min Act: -0.1700

Data Index: 844125 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 3.6781. Min Range: -3.6781

Max Act: 3.3020. Min Act: -0.1700

Data Index: 637029 (C4 (Web Text))

Max Activating Token Index: 308