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

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

Neuron 1719 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1897. Min Range: -5.1897

Max Act: 5.1897. Min Act: -0.1700

Data Index: 1199580 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7834. Min Act: -0.1700

Data Index: 267096 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7522. Min Act: -0.1700

Data Index: 39708 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.8147. Min Act: -0.1700

Data Index: 1063105 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7209. Min Act: -0.1700

Data Index: 161150 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6584. Min Act: -0.1700

Data Index: 870783 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6897. Min Act: -0.1700

Data Index: 423009 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6584. Min Act: -0.1700

Data Index: 708001 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7209. Min Act: -0.1700

Data Index: 394677 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6584. Min Act: -0.1700

Data Index: 1227015 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6584. Min Act: -0.1700

Data Index: 1336668 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6584. Min Act: -0.1700

Data Index: 1275257 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6272. Min Act: -0.1700

Data Index: 1141859 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.5959. Min Act: -0.1700

Data Index: 1304909 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6272. Min Act: -0.1700

Data Index: 577383 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.5959. Min Act: -0.1699

Data Index: 1316054 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6272. Min Act: -0.1700

Data Index: 374616 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6272. Min Act: -0.1700

Data Index: 414694 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6272. Min Act: -0.1700

Data Index: 230754 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.5647. Min Act: -0.1700

Data Index: 1290194 (C4 (Web Text))

Max Activating Token Index: 393