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

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

Neuron 1514 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: 4.0121. Min Range: -4.0121

Max Act: 4.0121. Min Act: -0.1700

Data Index: 53194 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.9595. Min Act: -0.1700

Data Index: 650491 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.9422. Min Act: -0.1651

Data Index: 1272859 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.9251. Min Act: -0.1700

Data Index: 1049209 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.8749. Min Act: -0.1700

Data Index: 201425 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.8882. Min Act: -0.1699

Data Index: 1106061 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.8517. Min Act: -0.1700

Data Index: 1324148 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.8394. Min Act: -0.1700

Data Index: 394835 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.8225. Min Act: -0.1700

Data Index: 898320 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.8322. Min Act: -0.1700

Data Index: 904372 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.8394. Min Act: -0.1700

Data Index: 259267 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.7821. Min Act: -0.1699

Data Index: 1003769 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.7798. Min Act: -0.1700

Data Index: 1051513 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.7998. Min Act: -0.1700

Data Index: 1075645 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.7918. Min Act: -0.1700

Data Index: 1290655 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.7819. Min Act: -0.1700

Data Index: 960447 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.7861. Min Act: -0.1700

Data Index: 639703 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.7819. Min Act: -0.1700

Data Index: 384151 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.8067. Min Act: -0.1700

Data Index: 645103 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 4.0121. Min Range: -4.0121

Max Act: 3.7490. Min Act: -0.1678

Data Index: 996770 (C4 (Web Text))

Max Activating Token Index: 256