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

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

Neuron 628 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: 3.5585. Min Range: -3.5585

Max Act: 3.5585. Min Act: -0.1700

Data Index: 355819 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.4645. Min Act: -0.1700

Data Index: 470442 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.4645. Min Act: -0.1700

Data Index: 748687 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.4331. Min Act: -0.1700

Data Index: 2042 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.4331. Min Act: -0.1700

Data Index: 1131174 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.4175. Min Act: -0.1700

Data Index: 678632 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3861. Min Act: -0.1700

Data Index: 120506 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3704. Min Act: -0.1700

Data Index: 203317 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3704. Min Act: -0.1700

Data Index: 1265078 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3547. Min Act: -0.1700

Data Index: 522695 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3704. Min Act: -0.1700

Data Index: 702223 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3704. Min Act: -0.1700

Data Index: 830414 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3390. Min Act: -0.1700

Data Index: 1153988 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3547. Min Act: -0.1700

Data Index: 1020724 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3547. Min Act: -0.1700

Data Index: 794821 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3390. Min Act: -0.1700

Data Index: 1091466 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3233. Min Act: -0.1700

Data Index: 420609 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3233. Min Act: -0.1700

Data Index: 427368 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3076. Min Act: -0.1700

Data Index: 811718 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 3.5585. Min Range: -3.5585

Max Act: 3.3076. Min Act: -0.1700

Data Index: 1142942 (C4 (Web Text))

Max Activating Token Index: 102