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

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

Neuron 2002 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: 3.4945. Min Range: -3.4945

Max Act: 3.4945. Min Act: -0.1700

Data Index: 1210188 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4788. Min Act: -0.1700

Data Index: 397309 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4631. Min Act: -0.1700

Data Index: 379766 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4475. Min Act: -0.1700

Data Index: 373382 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4475. Min Act: -0.1700

Data Index: 734930 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4318. Min Act: -0.1700

Data Index: 381337 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4475. Min Act: -0.1700

Data Index: 814629 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4318. Min Act: -0.1700

Data Index: 876950 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4161. Min Act: -0.1700

Data Index: 136540 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4161. Min Act: -0.1700

Data Index: 1114214 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4161. Min Act: -0.1700

Data Index: 11574 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4318. Min Act: -0.1700

Data Index: 1128424 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4318. Min Act: -0.1700

Data Index: 285468 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4318. Min Act: -0.1700

Data Index: 242592 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4161. Min Act: -0.1700

Data Index: 1130501 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4161. Min Act: -0.1700

Data Index: 1293673 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4318. Min Act: -0.1700

Data Index: 419930 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.4161. Min Act: -0.1700

Data Index: 579596 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.3847. Min Act: -0.1700

Data Index: 1055998 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 3.4945. Min Range: -3.4945

Max Act: 3.3847. Min Act: -0.1700

Data Index: 890934 (C4 (Web Text))

Max Activating Token Index: 151