Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 109 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.3047. Min Act: -0.1700

Data Index: 98756 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.3204. Min Act: -0.1700

Data Index: 71265 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.3204. Min Act: -0.1700

Data Index: 761512 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.3047. Min Act: -0.1700

Data Index: 572439 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.3204. Min Act: -0.1700

Data Index: 1180913 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2890. Min Act: -0.1700

Data Index: 210371 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2733. Min Act: -0.1700

Data Index: 1262104 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2576. Min Act: -0.1700

Data Index: 1323060 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2419. Min Act: -0.1700

Data Index: 545926 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2104. Min Act: -0.1700

Data Index: 418899 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2104. Min Act: -0.1700

Data Index: 441545 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2104. Min Act: -0.1700

Data Index: 711616 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2104. Min Act: -0.1700

Data Index: 34350 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.2104. Min Act: -0.1700

Data Index: 212317 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1241144 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.1947. Min Act: -0.1700

Data Index: 354011 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.1947. Min Act: -0.1700

Data Index: 325060 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.1947. Min Act: -0.1700

Data Index: 535610 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1264956 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 3.3204. Min Range: -3.3204

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1281096 (C4 (Web Text))

Max Activating Token Index: 316