Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 499 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.9160. Min Act: -0.1700
Data Index: 977371 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.8842. Min Act: -0.1700
Data Index: 1298553 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.9160. Min Act: -0.1700
Data Index: 863751 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.8842. Min Act: -0.1700
Data Index: 473285 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.8525. Min Act: -0.1700
Data Index: 768768 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.8525. Min Act: -0.1700
Data Index: 1040009 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.8047. Min Act: -0.1700
Data Index: 301193 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.8366. Min Act: -0.1700
Data Index: 730271 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.8207. Min Act: -0.1700
Data Index: 631941 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7888. Min Act: -0.1700
Data Index: 629379 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7888. Min Act: -0.1700
Data Index: 191290 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.8047. Min Act: -0.1700
Data Index: 817525 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7888. Min Act: -0.1700
Data Index: 639167 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7569. Min Act: -0.1700
Data Index: 1160840 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7729. Min Act: -0.1700
Data Index: 709472 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7410. Min Act: -0.1700
Data Index: 432153 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7569. Min Act: -0.1700
Data Index: 1516847 (Python Code)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7410. Min Act: -0.1700
Data Index: 232405 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7410. Min Act: -0.1700
Data Index: 25211 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9160. Min Range: -2.9160
Max Act: 2.7250. Min Act: -0.1700
Data Index: 1263281 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19