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

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

Neuron 877 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.3401. Min Range: -7.3401

Max Act: 7.3088. Min Act: -0.1700

Data Index: 985068 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 7.3401. Min Range: -7.3401

Max Act: 7.3401. Min Act: -0.1700

Data Index: 1427491 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 7.3401. Min Range: -7.3401

Max Act: 7.0901. Min Act: -0.1700

Data Index: 1530126 (Python Code)

Max Activating Token Index: 358

Text #3

Max Range: 7.3401. Min Range: -7.3401

Max Act: 7.1526. Min Act: -0.1700

Data Index: 1642373 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 7.3401. Min Range: -7.3401

Max Act: 7.0276. Min Act: -0.1700

Data Index: 1447676 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.9651. Min Act: -0.1700

Data Index: 1413887 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.9651. Min Act: -0.1700

Data Index: 1364386 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.9651. Min Act: -0.1700

Data Index: 1612844 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.9651. Min Act: -0.1700

Data Index: 1614080 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.9963. Min Act: -0.1700

Data Index: 1493087 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.9026. Min Act: -0.1700

Data Index: 1654439 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.9338. Min Act: -0.1700

Data Index: 1502657 (Python Code)

Max Activating Token Index: 367

Text #12

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.9026. Min Act: -0.1700

Data Index: 1652005 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.8088. Min Act: -0.1700

Data Index: 310331 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.8713. Min Act: -0.1700

Data Index: 1630966 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.7776. Min Act: -0.1700

Data Index: 239311 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.7776. Min Act: -0.1700

Data Index: 1426569 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.7776. Min Act: -0.1700

Data Index: 1569907 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.7463. Min Act: -0.1700

Data Index: 1413359 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 7.3401. Min Range: -7.3401

Max Act: 6.7463. Min Act: -0.1700

Data Index: 1103358 (C4 (Web Text))

Max Activating Token Index: 53