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

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

Neuron 361 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: 3.7484. Min Range: -3.7484

Max Act: 3.7484. Min Act: -0.1700

Data Index: 509696 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.7328. Min Act: -0.1700

Data Index: 1235913 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.7172. Min Act: -0.1700

Data Index: 746051 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.7172. Min Act: -0.1700

Data Index: 931511 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.7015. Min Act: -0.1700

Data Index: 8219 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6546. Min Act: -0.1700

Data Index: 20349 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6389. Min Act: -0.1700

Data Index: 302031 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6389. Min Act: -0.1700

Data Index: 480797 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6546. Min Act: -0.1700

Data Index: 197560 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6233. Min Act: -0.1700

Data Index: 427621 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6233. Min Act: -0.1700

Data Index: 1285241 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6076. Min Act: -0.1700

Data Index: 1124229 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6389. Min Act: -0.1700

Data Index: 1181835 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6076. Min Act: -0.1700

Data Index: 89888 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6076. Min Act: -0.1700

Data Index: 845135 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.6233. Min Act: -0.1700

Data Index: 824763 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5763. Min Act: -0.1700

Data Index: 831380 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5763. Min Act: -0.1700

Data Index: 1080082 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5919. Min Act: -0.1700

Data Index: 434701 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 3.7484. Min Range: -3.7484

Max Act: 3.5763. Min Act: -0.1700

Data Index: 167882 (C4 (Web Text))

Max Activating Token Index: 336