Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 37 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.9444. Min Act: -0.1700
Data Index: 1560576 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.8333. Min Act: -0.1700
Data Index: 818899 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.8333. Min Act: -0.1700
Data Index: 1500824 (Python Code)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7856. Min Act: -0.1700
Data Index: 467247 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7856. Min Act: -0.1700
Data Index: 1421532 (Python Code)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7856. Min Act: -0.1700
Data Index: 1176665 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.8015. Min Act: -0.1700
Data Index: 509405 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7696. Min Act: -0.1700
Data Index: 1544930 (Python Code)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7377. Min Act: -0.1700
Data Index: 858833 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7537. Min Act: -0.1700
Data Index: 1585923 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7696. Min Act: -0.1700
Data Index: 1441323 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7537. Min Act: -0.1700
Data Index: 1098856 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7696. Min Act: -0.1700
Data Index: 1304536 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7377. Min Act: -0.1700
Data Index: 1459526 (Python Code)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7696. Min Act: -0.1700
Data Index: 973495 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7217. Min Act: -0.1700
Data Index: 967809 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7537. Min Act: -0.1700
Data Index: 13944 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7537. Min Act: -0.1700
Data Index: 408218 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7377. Min Act: -0.1700
Data Index: 1062164 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9444. Min Range: -2.9444
Max Act: 2.7377. Min Act: -0.1700
Data Index: 1476913 (Python Code)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19