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

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

Neuron 503 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: 3.7885. Min Range: -3.7885

Max Act: 3.7885. Min Act: -0.1700

Data Index: 1225535 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.7259. Min Act: -0.1700

Data Index: 741239 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6946. Min Act: -0.1700

Data Index: 1297088 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.7259. Min Act: -0.1700

Data Index: 838981 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.7259. Min Act: -0.1700

Data Index: 324878 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6633. Min Act: -0.1700

Data Index: 965018 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6946. Min Act: -0.1700

Data Index: 1101401 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6320. Min Act: -0.1700

Data Index: 1232144 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6320. Min Act: -0.1700

Data Index: 854951 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6007. Min Act: -0.1700

Data Index: 983459 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6320. Min Act: -0.1700

Data Index: 556791 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6320. Min Act: -0.1700

Data Index: 392358 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6320. Min Act: -0.1700

Data Index: 463539 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6007. Min Act: -0.1700

Data Index: 1308269 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.5694. Min Act: -0.1700

Data Index: 595698 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6007. Min Act: -0.1700

Data Index: 443700 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6320. Min Act: -0.1700

Data Index: 519323 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.6007. Min Act: -0.1700

Data Index: 66441 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.5380. Min Act: -0.1700

Data Index: 2524 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 3.7885. Min Range: -3.7885

Max Act: 3.5694. Min Act: -0.1700

Data Index: 1021717 (C4 (Web Text))

Max Activating Token Index: 241