Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1921 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.0553. Min Range: -2.0553
Max Act: 2.0553. Min Act: -0.1700
Data Index: 1319193 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0553. Min Range: -2.0553
Max Act: 2.0048. Min Act: -0.1700
Data Index: 170619 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9709. Min Act: -0.1700
Data Index: 397588 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9709. Min Act: -0.1700
Data Index: 175577 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9709. Min Act: -0.1700
Data Index: 480815 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9625. Min Act: -0.1700
Data Index: 1431089 (Python Code)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9540. Min Act: -0.1700
Data Index: 167918 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9370. Min Act: -0.1700
Data Index: 1629330 (Python Code)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9285. Min Act: -0.1699
Data Index: 1310628 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9285. Min Act: -0.1700
Data Index: 154374 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9200. Min Act: -0.1700
Data Index: 568911 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9115. Min Act: -0.1700
Data Index: 1442879 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9115. Min Act: -0.1700
Data Index: 1627766 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9115. Min Act: -0.1700
Data Index: 1375784 (Python Code)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9200. Min Act: -0.1700
Data Index: 1382482 (Python Code)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9115. Min Act: -0.1699
Data Index: 1367246 (Python Code)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9030. Min Act: -0.1700
Data Index: 1057777 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.8945. Min Act: -0.1700
Data Index: 1498679 (Python Code)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.9030. Min Act: -0.1700
Data Index: 1270661 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0553. Min Range: -2.0553
Max Act: 1.8945. Min Act: -0.1700
Data Index: 1496826 (Python Code)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19