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

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

Neuron 213 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: 3.3866. Min Range: -3.3866

Max Act: 3.3866. Min Act: -0.1700

Data Index: 1288487 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.3709. Min Act: -0.1700

Data Index: 1301449 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.3238. Min Act: -0.1700

Data Index: 249362 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.3552. Min Act: -0.1700

Data Index: 264120 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2452. Min Act: -0.1700

Data Index: 434655 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2610. Min Act: -0.1700

Data Index: 523898 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2924. Min Act: -0.1700

Data Index: 764291 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2767. Min Act: -0.1700

Data Index: 1199776 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2767. Min Act: -0.1700

Data Index: 192062 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2295. Min Act: -0.1700

Data Index: 347591 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2452. Min Act: -0.1700

Data Index: 779857 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2610. Min Act: -0.1700

Data Index: 960358 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2138. Min Act: -0.1700

Data Index: 769571 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2610. Min Act: -0.1700

Data Index: 309943 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2138. Min Act: -0.1700

Data Index: 36740 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2138. Min Act: -0.1700

Data Index: 1283172 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2452. Min Act: -0.1700

Data Index: 873961 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2295. Min Act: -0.1700

Data Index: 701796 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.1823. Min Act: -0.1700

Data Index: 624648 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 3.3866. Min Range: -3.3866

Max Act: 3.2138. Min Act: -0.1700

Data Index: 825622 (C4 (Web Text))

Max Activating Token Index: 273