Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 187 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0814. Min Act: -0.1700

Data Index: 1491029 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0814. Min Act: -0.1700

Data Index: 1640944 (Python Code)

Max Activating Token Index: 634

Text #2

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0498. Min Act: -0.1700

Data Index: 814577 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0340. Min Act: -0.1700

Data Index: 242331 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0340. Min Act: -0.1700

Data Index: 430977 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0340. Min Act: -0.1700

Data Index: 1164195 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0182. Min Act: -0.1700

Data Index: 408682 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0340. Min Act: -0.1700

Data Index: 1273686 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0182. Min Act: -0.1700

Data Index: 1135015 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0182. Min Act: -0.1700

Data Index: 860607 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0024. Min Act: -0.1700

Data Index: 794636 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0024. Min Act: -0.1700

Data Index: 482756 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0024. Min Act: -0.1700

Data Index: 557001 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0024. Min Act: -0.1700

Data Index: 585924 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 3.0814. Min Range: -3.0814

Max Act: 3.0024. Min Act: -0.1700

Data Index: 1199829 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 3.0814. Min Range: -3.0814

Max Act: 2.9866. Min Act: -0.1700

Data Index: 758968 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 3.0814. Min Range: -3.0814

Max Act: 2.9866. Min Act: -0.1700

Data Index: 885337 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 3.0814. Min Range: -3.0814

Max Act: 2.9866. Min Act: -0.1700

Data Index: 498009 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 3.0814. Min Range: -3.0814

Max Act: 2.9866. Min Act: -0.1700

Data Index: 922145 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 3.0814. Min Range: -3.0814

Max Act: 2.9866. Min Act: -0.1700

Data Index: 964031 (C4 (Web Text))

Max Activating Token Index: 275