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

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

Neuron 1566 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: 3.9049. Min Range: -3.9049

Max Act: 3.9049. Min Act: -0.1700

Data Index: 391225 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8736. Min Act: -0.1700

Data Index: 404970 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8423. Min Act: -0.1700

Data Index: 230451 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8110. Min Act: -0.1700

Data Index: 1167496 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8423. Min Act: -0.1700

Data Index: 1142227 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8110. Min Act: -0.1700

Data Index: 1079350 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8423. Min Act: -0.1700

Data Index: 138280 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8736. Min Act: -0.1700

Data Index: 383075 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7798. Min Act: -0.1700

Data Index: 109308 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8110. Min Act: -0.1700

Data Index: 1231228 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7798. Min Act: -0.1700

Data Index: 533755 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 118815 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8736. Min Act: -0.1700

Data Index: 618049 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 1081664 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8423. Min Act: -0.1700

Data Index: 618709 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 296384 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.8110. Min Act: -0.1700

Data Index: 59962 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 287869 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7485. Min Act: -0.1700

Data Index: 202132 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 3.9049. Min Range: -3.9049

Max Act: 3.7798. Min Act: -0.1700

Data Index: 1075858 (C4 (Web Text))

Max Activating Token Index: 336