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

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

Neuron 841 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: 7.1272. Min Range: -7.1272

Max Act: 7.1272. Min Act: -0.1700

Data Index: 1148996 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.9397. Min Act: -0.1700

Data Index: 693928 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.9084. Min Act: -0.1700

Data Index: 973634 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.8147. Min Act: -0.1700

Data Index: 713383 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.9397. Min Act: -0.1700

Data Index: 511433 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.7834. Min Act: -0.1700

Data Index: 1300136 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.7522. Min Act: -0.1700

Data Index: 598992 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.8772. Min Act: -0.1700

Data Index: 73036 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.7522. Min Act: -0.1700

Data Index: 707306 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.8772. Min Act: -0.1700

Data Index: 249765 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.8147. Min Act: -0.1700

Data Index: 661241 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.6584. Min Act: -0.1700

Data Index: 1359343 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.7209. Min Act: -0.1700

Data Index: 1214231 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.6272. Min Act: -0.1700

Data Index: 1320295 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.5959. Min Act: -0.1700

Data Index: 985906 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.5959. Min Act: -0.1700

Data Index: 900008 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.6897. Min Act: -0.1700

Data Index: 324227 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.5647. Min Act: -0.1700

Data Index: 931708 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.5647. Min Act: -0.1700

Data Index: 357554 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 7.1272. Min Range: -7.1272

Max Act: 6.6584. Min Act: -0.1700

Data Index: 240780 (C4 (Web Text))

Max Activating Token Index: 121