Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 889 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.9100. Min Act: -0.1700

Data Index: 1099734 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.8768. Min Act: -0.1700

Data Index: 532223 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.8750. Min Act: -0.1700

Data Index: 36667 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.7767. Min Act: -0.1700

Data Index: 476183 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.7218. Min Act: -0.1700

Data Index: 1098823 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.7034. Min Act: -0.1700

Data Index: 972081 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6935. Min Act: -0.1700

Data Index: 983856 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6820. Min Act: -0.1700

Data Index: 22904 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6633. Min Act: -0.1700

Data Index: 268669 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6569. Min Act: -0.1700

Data Index: 956565 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6657. Min Act: -0.1700

Data Index: 534038 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6597. Min Act: -0.1700

Data Index: 529221 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6261. Min Act: -0.1700

Data Index: 433934 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6333. Min Act: -0.1700

Data Index: 929573 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6354. Min Act: -0.1700

Data Index: 184530 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6298. Min Act: -0.1700

Data Index: 722003 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.6096. Min Act: -0.1700

Data Index: 63160 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.5786. Min Act: -0.1700

Data Index: 1030329 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.5797. Min Act: -0.1700

Data Index: 134187 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 2.9100. Min Range: -2.9100

Max Act: 2.5690. Min Act: -0.1700

Data Index: 770583 (C4 (Web Text))

Max Activating Token Index: 599