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

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

Neuron 1817 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: 3.9558. Min Range: -3.9558

Max Act: 3.9558. Min Act: -0.1700

Data Index: 88646 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.7681. Min Act: -0.1700

Data Index: 63871 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6429. Min Act: -0.1700

Data Index: 825248 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6742. Min Act: -0.1700

Data Index: 1184392 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6742. Min Act: -0.1700

Data Index: 194621 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.7055. Min Act: -0.1700

Data Index: 1233284 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6742. Min Act: -0.1700

Data Index: 591018 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6116. Min Act: -0.1700

Data Index: 1311318 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6429. Min Act: -0.1700

Data Index: 51174 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6116. Min Act: -0.1700

Data Index: 935143 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.5803. Min Act: -0.1700

Data Index: 1208567 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6116. Min Act: -0.1700

Data Index: 320452 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6116. Min Act: -0.1700

Data Index: 1145458 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.6429. Min Act: -0.1700

Data Index: 689682 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.5490. Min Act: -0.1700

Data Index: 588706 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.5803. Min Act: -0.1700

Data Index: 156183 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.5803. Min Act: -0.1700

Data Index: 834475 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.5177. Min Act: -0.1700

Data Index: 1141544 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.5803. Min Act: -0.1700

Data Index: 350239 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 3.9558. Min Range: -3.9558

Max Act: 3.5803. Min Act: -0.1700

Data Index: 774034 (C4 (Web Text))

Max Activating Token Index: 836