Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 334 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.8743. Min Act: -0.1700

Data Index: 50121 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.8743. Min Act: -0.1700

Data Index: 785907 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.8118. Min Act: -0.1700

Data Index: 956640 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7961. Min Act: -0.1700

Data Index: 1034192 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7961. Min Act: -0.1700

Data Index: 739404 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7649. Min Act: -0.1700

Data Index: 1106146 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7023. Min Act: -0.1700

Data Index: 480652 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7336. Min Act: -0.1700

Data Index: 502670 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7492. Min Act: -0.1699

Data Index: 861572 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.6710. Min Act: -0.1700

Data Index: 132811 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7023. Min Act: -0.1700

Data Index: 107097 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.6866. Min Act: -0.1700

Data Index: 1032570 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.6866. Min Act: -0.1700

Data Index: 279380 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.6710. Min Act: -0.1700

Data Index: 1558832 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.6710. Min Act: -0.1700

Data Index: 1271511 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.6710. Min Act: -0.1700

Data Index: 122502 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7179. Min Act: -0.1700

Data Index: 405356 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.6710. Min Act: -0.1700

Data Index: 1103486 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7023. Min Act: -0.1700

Data Index: 484563 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.6866. Min Act: -0.1700

Data Index: 1134098 (C4 (Web Text))

Max Activating Token Index: 869