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

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

Neuron 1060 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: 3.9968. Min Range: -3.9968

Max Act: 3.9968. Min Act: -0.1700

Data Index: 378657 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.8717. Min Act: -0.1700

Data Index: 745566 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.8404. Min Act: -0.1700

Data Index: 1101168 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.8404. Min Act: -0.1700

Data Index: 971782 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.8404. Min Act: -0.1700

Data Index: 683037 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.8717. Min Act: -0.1700

Data Index: 570454 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.8092. Min Act: -0.1700

Data Index: 41935 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7466. Min Act: -0.1700

Data Index: 713100 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7466. Min Act: -0.1700

Data Index: 165725 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7779. Min Act: -0.1700

Data Index: 302689 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7153. Min Act: -0.1700

Data Index: 60185 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7779. Min Act: -0.1700

Data Index: 1086859 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7466. Min Act: -0.1700

Data Index: 510768 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7466. Min Act: -0.1700

Data Index: 930066 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7779. Min Act: -0.1700

Data Index: 1312745 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.8092. Min Act: -0.1700

Data Index: 85836 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7779. Min Act: -0.1700

Data Index: 263034 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7779. Min Act: -0.1700

Data Index: 593251 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7153. Min Act: -0.1700

Data Index: 205115 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 3.9968. Min Range: -3.9968

Max Act: 3.7466. Min Act: -0.1700

Data Index: 387836 (C4 (Web Text))

Max Activating Token Index: 261