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

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

Neuron 1411 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.2236. Min Act: -0.1700

Data Index: 1304857 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1764. Min Act: -0.1700

Data Index: 1108033 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.1764. Min Act: -0.1700

Data Index: 1023585 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0345. Min Act: -0.1700

Data Index: 1072412 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0819. Min Act: -0.1700

Data Index: 412553 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0187. Min Act: -0.1700

Data Index: 1232224 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0819. Min Act: -0.1700

Data Index: 45214 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0187. Min Act: -0.1700

Data Index: 827059 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0029. Min Act: -0.1700

Data Index: 1199326 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0819. Min Act: -0.1700

Data Index: 373533 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0345. Min Act: -0.1700

Data Index: 671994 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0819. Min Act: -0.1700

Data Index: 854657 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0187. Min Act: -0.1700

Data Index: 1201753 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0029. Min Act: -0.1700

Data Index: 179476 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0187. Min Act: -0.1700

Data Index: 133020 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 3.2236. Min Range: -3.2236

Max Act: 2.9871. Min Act: -0.1700

Data Index: 1129362 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 3.2236. Min Range: -3.2236

Max Act: 2.9555. Min Act: -0.1700

Data Index: 1343426 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0029. Min Act: -0.1700

Data Index: 97723 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0029. Min Act: -0.1700

Data Index: 501292 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 3.2236. Min Range: -3.2236

Max Act: 3.0345. Min Act: -0.1700

Data Index: 1066165 (C4 (Web Text))

Max Activating Token Index: 396