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

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

Neuron 446 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: 7.5707. Min Range: -7.5707

Max Act: 7.5707. Min Act: -0.1700

Data Index: 469909 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.5082. Min Act: -0.1700

Data Index: 841299 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.3207. Min Act: -0.1700

Data Index: 980855 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.3832. Min Act: -0.1700

Data Index: 38452 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.3207. Min Act: -0.1700

Data Index: 660284 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.1957. Min Act: -0.1700

Data Index: 1275396 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.3207. Min Act: -0.1700

Data Index: 288816 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.1957. Min Act: -0.1700

Data Index: 844817 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.1645. Min Act: -0.1700

Data Index: 436958 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.2582. Min Act: -0.1700

Data Index: 859991 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.1645. Min Act: -0.1700

Data Index: 572874 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.1332. Min Act: -0.1700

Data Index: 986766 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.0395. Min Act: -0.1700

Data Index: 80127 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.0082. Min Act: -0.1700

Data Index: 440115 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.0395. Min Act: -0.1700

Data Index: 1146123 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.0082. Min Act: -0.1700

Data Index: 1177139 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.1020. Min Act: -0.1700

Data Index: 686418 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.0707. Min Act: -0.1700

Data Index: 484006 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 7.5707. Min Range: -7.5707

Max Act: 6.9770. Min Act: -0.1700

Data Index: 951086 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 7.5707. Min Range: -7.5707

Max Act: 7.0395. Min Act: -0.1700

Data Index: 751075 (C4 (Web Text))

Max Activating Token Index: 147