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

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

Neuron 305 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.7905. Min Act: -0.1700

Data Index: 990757 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.6653. Min Act: -0.1700

Data Index: 331173 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.5714. Min Act: -0.1700

Data Index: 1036184 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.3519. Min Act: -0.1700

Data Index: 280439 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.3519. Min Act: -0.1700

Data Index: 467892 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.3048. Min Act: -0.1700

Data Index: 880553 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.3362. Min Act: -0.1700

Data Index: 811123 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1948. Min Act: -0.1700

Data Index: 1035884 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1948. Min Act: -0.1700

Data Index: 290568 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1633. Min Act: -0.1700

Data Index: 853814 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1633. Min Act: -0.1700

Data Index: 1333442 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1791. Min Act: -0.1700

Data Index: 397945 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1161. Min Act: -0.1700

Data Index: 698917 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1318. Min Act: -0.1700

Data Index: 277126 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.0687. Min Act: -0.1700

Data Index: 577615 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1161. Min Act: -0.1700

Data Index: 1359029 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.1003. Min Act: -0.1700

Data Index: 300430 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.0845. Min Act: -0.1700

Data Index: 574095 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.0845. Min Act: -0.1700

Data Index: 1340910 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 3.7905. Min Range: -3.7905

Max Act: 3.0687. Min Act: -0.1700

Data Index: 264815 (C4 (Web Text))

Max Activating Token Index: 289