Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2039 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.8900. Min Act: -0.1700
Data Index: 1170723 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.8583. Min Act: -0.1700
Data Index: 203742 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.8424. Min Act: -0.1700
Data Index: 211807 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.8106. Min Act: -0.1700
Data Index: 1552032 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.8583. Min Act: -0.1700
Data Index: 1215084 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.8265. Min Act: -0.1700
Data Index: 850052 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.8265. Min Act: -0.1700
Data Index: 1249418 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.8106. Min Act: -0.1700
Data Index: 123988 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.7468. Min Act: -0.1700
Data Index: 562062 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.7308. Min Act: -0.1700
Data Index: 19245 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.7308. Min Act: -0.1700
Data Index: 439288 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.7148. Min Act: -0.1700
Data Index: 1334816 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.7148. Min Act: -0.1700
Data Index: 1014588 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.7308. Min Act: -0.1700
Data Index: 6807 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.6988. Min Act: -0.1700
Data Index: 948688 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.6508. Min Act: -0.1700
Data Index: 1332157 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.6828. Min Act: -0.1700
Data Index: 564639 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.6668. Min Act: -0.1700
Data Index: 498597 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.6668. Min Act: -0.1700
Data Index: 1223945 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8900. Min Range: -2.8900
Max Act: 2.6508. Min Act: -0.1700
Data Index: 1291688 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19