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

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

Neuron 28 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: 3.9112. Min Range: -3.9112

Max Act: 3.9112. Min Act: -0.1700

Data Index: 3894 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.7861. Min Act: -0.1700

Data Index: 677213 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.7548. Min Act: -0.1700

Data Index: 1173321 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.7235. Min Act: -0.1700

Data Index: 888016 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.7548. Min Act: -0.1700

Data Index: 1309120 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.7235. Min Act: -0.1700

Data Index: 598932 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6922. Min Act: -0.1700

Data Index: 594482 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.7235. Min Act: -0.1700

Data Index: 1223936 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.7235. Min Act: -0.1700

Data Index: 67504 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6922. Min Act: -0.1700

Data Index: 80501 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6609. Min Act: -0.1700

Data Index: 913754 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6922. Min Act: -0.1700

Data Index: 1351537 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6609. Min Act: -0.1700

Data Index: 873735 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6609. Min Act: -0.1700

Data Index: 139349 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1224863 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1205068 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.7235. Min Act: -0.1700

Data Index: 1067199 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6609. Min Act: -0.1700

Data Index: 529623 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6609. Min Act: -0.1700

Data Index: 7702 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.6609. Min Act: -0.1700

Data Index: 213867 (C4 (Web Text))

Max Activating Token Index: 274