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

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

Neuron 113 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: 7.1011. Min Range: -7.1011

Max Act: 7.1011. Min Act: -0.1700

Data Index: 128624 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 7.1011. Min Range: -7.1011

Max Act: 7.1011. Min Act: -0.1700

Data Index: 862486 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.9136. Min Act: -0.1700

Data Index: 100142 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.9136. Min Act: -0.1700

Data Index: 1497754 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.8511. Min Act: -0.1700

Data Index: 1288382 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.7886. Min Act: -0.1700

Data Index: 1335784 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.8198. Min Act: -0.1700

Data Index: 1474624 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.7261. Min Act: -0.1700

Data Index: 1498364 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6636. Min Act: -0.1700

Data Index: 944256 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6323. Min Act: -0.1700

Data Index: 1489515 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6323. Min Act: -0.1700

Data Index: 1516978 (Python Code)

Max Activating Token Index: 233

Text #11

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6323. Min Act: -0.1700

Data Index: 557018 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6948. Min Act: -0.1700

Data Index: 350833 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6011. Min Act: -0.1700

Data Index: 191939 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6323. Min Act: -0.1700

Data Index: 1562010 (Python Code)

Max Activating Token Index: 179

Text #15

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6636. Min Act: -0.1700

Data Index: 484734 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.6323. Min Act: -0.1700

Data Index: 509550 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.4761. Min Act: -0.1700

Data Index: 895521 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.4136. Min Act: -0.1700

Data Index: 395982 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 7.1011. Min Range: -7.1011

Max Act: 6.5073. Min Act: -0.1700

Data Index: 1173677 (C4 (Web Text))

Max Activating Token Index: 1010