Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1887 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.1825. Min Act: -0.1700

Data Index: 1053794 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0575. Min Act: -0.1700

Data Index: 87285 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0575. Min Act: -0.1700

Data Index: 234411 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0263. Min Act: -0.1700

Data Index: 476713 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9638. Min Act: -0.1700

Data Index: 930923 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9638. Min Act: -0.1700

Data Index: 516837 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9638. Min Act: -0.1700

Data Index: 859505 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9638. Min Act: -0.1700

Data Index: 991053 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9325. Min Act: -0.1700

Data Index: 120195 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9638. Min Act: -0.1700

Data Index: 1256820 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9950. Min Act: -0.1700

Data Index: 733427 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9013. Min Act: -0.1700

Data Index: 299120 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.8700. Min Act: -0.1700

Data Index: 684202 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9013. Min Act: -0.1700

Data Index: 125569 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9013. Min Act: -0.1700

Data Index: 467219 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.8388. Min Act: -0.1700

Data Index: 851977 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9013. Min Act: -0.1700

Data Index: 313902 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.8700. Min Act: -0.1700

Data Index: 867627 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.8700. Min Act: -0.1700

Data Index: 614076 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.8388. Min Act: -0.1700

Data Index: 377070 (C4 (Web Text))

Max Activating Token Index: 341