Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2004 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1452. Min Range: -4.1452
Max Act: 4.1452. Min Act: -0.1700
Data Index: 662627 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1452. Min Range: -4.1452
Max Act: 4.0514. Min Act: -0.1700
Data Index: 1574090 (Python Code)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1452. Min Range: -4.1452
Max Act: 4.0514. Min Act: -0.1699
Data Index: 863457 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1452. Min Range: -4.1452
Max Act: 4.0202. Min Act: -0.1700
Data Index: 849857 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1452. Min Range: -4.1452
Max Act: 4.0202. Min Act: -0.1700
Data Index: 413979 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9576. Min Act: -0.1700
Data Index: 275864 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9889. Min Act: -0.1700
Data Index: 1499742 (Python Code)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9576. Min Act: -0.1700
Data Index: 1583888 (Python Code)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9889. Min Act: -0.1700
Data Index: 1161572 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1452. Min Range: -4.1452
Max Act: 4.0202. Min Act: -0.1700
Data Index: 613563 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9889. Min Act: -0.1700
Data Index: 1050606 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1452. Min Range: -4.1452
Max Act: 4.0202. Min Act: -0.1699
Data Index: 1380290 (Python Code)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9576. Min Act: -0.1700
Data Index: 308598 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9576. Min Act: -0.1700
Data Index: 46725 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.8951. Min Act: -0.1700
Data Index: 1513360 (Python Code)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9264. Min Act: -0.1700
Data Index: 1475389 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9264. Min Act: -0.1700
Data Index: 1485798 (Python Code)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9576. Min Act: -0.1700
Data Index: 1559467 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.9264. Min Act: -0.1700
Data Index: 1380844 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1452. Min Range: -4.1452
Max Act: 3.8951. Min Act: -0.1700
Data Index: 73854 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19