Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 46 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.1760. Min Range: -6.1760
Max Act: 6.1760. Min Act: -0.1700
Data Index: 386203 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.9885. Min Act: -0.1700
Data Index: 34195 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1760. Min Range: -6.1760
Max Act: 6.0822. Min Act: -0.1700
Data Index: 84949 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1760. Min Range: -6.1760
Max Act: 6.0510. Min Act: -0.1700
Data Index: 447283 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1760. Min Range: -6.1760
Max Act: 6.0197. Min Act: -0.1700
Data Index: 573907 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.8635. Min Act: -0.1700
Data Index: 833870 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.8322. Min Act: -0.1700
Data Index: 241905 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.8010. Min Act: -0.1700
Data Index: 560498 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.8010. Min Act: -0.1700
Data Index: 339340 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.7072. Min Act: -0.1700
Data Index: 623579 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.6760. Min Act: -0.1700
Data Index: 796491 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.6760. Min Act: -0.1700
Data Index: 1216328 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.6135. Min Act: -0.1700
Data Index: 508267 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.5510. Min Act: -0.1700
Data Index: 155264 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.5197. Min Act: -0.1700
Data Index: 83923 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.5510. Min Act: -0.1700
Data Index: 1072219 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.4885. Min Act: -0.1700
Data Index: 127085 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.4885. Min Act: -0.1700
Data Index: 850102 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.4260. Min Act: -0.1700
Data Index: 682078 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1760. Min Range: -6.1760
Max Act: 5.5197. Min Act: -0.1700
Data Index: 1259947 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19