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

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

Neuron 1286 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0945. Min Range: -7.0945

Max Act: 7.0945. Min Act: -0.1682

Data Index: 177933 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 7.0945. Min Range: -7.0945

Max Act: 7.0633. Min Act: -0.1696

Data Index: 1184198 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 7.0945. Min Range: -7.0945

Max Act: 7.0008. Min Act: -0.1700

Data Index: 537575 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.9383. Min Act: -0.1700

Data Index: 1139117 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.9383. Min Act: -0.1700

Data Index: 198489 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.8445. Min Act: -0.1700

Data Index: 217695 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.7508. Min Act: -0.1700

Data Index: 269193 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.8133. Min Act: -0.1700

Data Index: 710066 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.7508. Min Act: -0.1700

Data Index: 351584 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.7820. Min Act: -0.1700

Data Index: 747122 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.7195. Min Act: -0.1700

Data Index: 464838 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.6883. Min Act: -0.1700

Data Index: 1205094 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.7820. Min Act: -0.1700

Data Index: 1104792 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.7508. Min Act: -0.1700

Data Index: 16099 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.6883. Min Act: -0.1700

Data Index: 394150 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.6258. Min Act: -0.1700

Data Index: 433125 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.6570. Min Act: -0.1700

Data Index: 640408 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.6570. Min Act: -0.1700

Data Index: 905993 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.6570. Min Act: -0.1699

Data Index: 1186077 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 7.0945. Min Range: -7.0945

Max Act: 6.6258. Min Act: -0.1700

Data Index: 1235318 (C4 (Web Text))

Max Activating Token Index: 151