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

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

Neuron 126 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2939. Min Act: -0.1700

Data Index: 563576 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2624. Min Act: -0.1700

Data Index: 89849 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2624. Min Act: -0.1700

Data Index: 69764 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2624. Min Act: -0.1700

Data Index: 1073671 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2153. Min Act: -0.1700

Data Index: 1107360 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2153. Min Act: -0.1700

Data Index: 574360 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2153. Min Act: -0.1700

Data Index: 1313434 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1996. Min Act: -0.1700

Data Index: 327006 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2153. Min Act: -0.1700

Data Index: 897689 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1996. Min Act: -0.1700

Data Index: 281572 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2310. Min Act: -0.1700

Data Index: 263335 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2153. Min Act: -0.1700

Data Index: 1341738 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1838. Min Act: -0.1700

Data Index: 883582 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1681. Min Act: -0.1700

Data Index: 892369 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1838. Min Act: -0.1700

Data Index: 1275403 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1996. Min Act: -0.1700

Data Index: 1258172 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1996. Min Act: -0.1700

Data Index: 396042 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1996. Min Act: -0.1700

Data Index: 1189966 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1838. Min Act: -0.1700

Data Index: 534643 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1523. Min Act: -0.1700

Data Index: 782024 (C4 (Web Text))

Max Activating Token Index: 5