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

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

Neuron 350 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: 5.0070. Min Range: -5.0070

Max Act: 5.0070. Min Act: -0.1700

Data Index: 1063191 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.9757. Min Act: -0.1700

Data Index: 870332 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.8820. Min Act: -0.1700

Data Index: 584405 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.8195. Min Act: -0.1700

Data Index: 190574 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.8507. Min Act: -0.1700

Data Index: 187112 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.8507. Min Act: -0.1700

Data Index: 133845 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.7570. Min Act: -0.1700

Data Index: 204591 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.9132. Min Act: -0.1699

Data Index: 525040 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.8820. Min Act: -0.1700

Data Index: 356027 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.7257. Min Act: -0.1700

Data Index: 278325 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.7882. Min Act: -0.1700

Data Index: 455730 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.6945. Min Act: -0.1700

Data Index: 610527 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.6945. Min Act: -0.1700

Data Index: 1248399 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.7882. Min Act: -0.1700

Data Index: 214060 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.8820. Min Act: -0.1700

Data Index: 1154967 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.7882. Min Act: -0.1700

Data Index: 1128220 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.6320. Min Act: -0.1700

Data Index: 990122 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.6945. Min Act: -0.1700

Data Index: 929445 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.8195. Min Act: -0.1700

Data Index: 570045 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 5.0070. Min Range: -5.0070

Max Act: 4.6320. Min Act: -0.1700

Data Index: 727769 (C4 (Web Text))

Max Activating Token Index: 567