Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 80 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.2851. Min Act: -0.1700
Data Index: 1343637 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.1288. Min Act: -0.1700
Data Index: 1306892 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.2226. Min Act: -0.1700
Data Index: 1428564 (Python Code)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.1601. Min Act: -0.1700
Data Index: 1494624 (Python Code)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.1601. Min Act: -0.1700
Data Index: 1380865 (Python Code)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0975. Min Act: -0.1700
Data Index: 1635093 (Python Code)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0663. Min Act: -0.1700
Data Index: 456947 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.1288. Min Act: -0.1700
Data Index: 490951 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0975. Min Act: -0.1700
Data Index: 1459420 (Python Code)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0663. Min Act: -0.1700
Data Index: 694548 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0350. Min Act: -0.1700
Data Index: 1373807 (Python Code)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0350. Min Act: -0.1700
Data Index: 1306869 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0350. Min Act: -0.1700
Data Index: 829403 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0038. Min Act: -0.1700
Data Index: 1609382 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2851. Min Range: -4.2851
Max Act: 3.9725. Min Act: -0.1700
Data Index: 1613700 (Python Code)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2851. Min Range: -4.2851
Max Act: 3.9412. Min Act: -0.1700
Data Index: 1469442 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2851. Min Range: -4.2851
Max Act: 4.0038. Min Act: -0.1700
Data Index: 634554 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2851. Min Range: -4.2851
Max Act: 3.9412. Min Act: -0.1700
Data Index: 1387685 (Python Code)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2851. Min Range: -4.2851
Max Act: 3.9100. Min Act: -0.1700
Data Index: 657255 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2851. Min Range: -4.2851
Max Act: 3.9412. Min Act: -0.1700
Data Index: 1616869 (Python Code)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19