Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1002 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0049. Min Range: -3.0049
Max Act: 3.0049. Min Act: -0.1700
Data Index: 1619937 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0049. Min Range: -3.0049
Max Act: 3.0049. Min Act: -0.1699
Data Index: 1613101 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9733. Min Act: -0.1700
Data Index: 1535236 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9891. Min Act: -0.1700
Data Index: 1638198 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9733. Min Act: -0.1700
Data Index: 1439517 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9574. Min Act: -0.1697
Data Index: 1516688 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9733. Min Act: -0.1700
Data Index: 1656260 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9574. Min Act: -0.1700
Data Index: 1503078 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9574. Min Act: -0.1700
Data Index: 1581596 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9416. Min Act: -0.1700
Data Index: 1632045 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9416. Min Act: -0.1700
Data Index: 1636418 (Python Code)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9416. Min Act: -0.1700
Data Index: 1649861 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9416. Min Act: -0.1698
Data Index: 1554006 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9416. Min Act: -0.1699
Data Index: 1462685 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9416. Min Act: -0.1692
Data Index: 1573811 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9574. Min Act: -0.1700
Data Index: 1444834 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9416. Min Act: -0.1700
Data Index: 280077 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9257. Min Act: -0.1699
Data Index: 1608619 (Python Code)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9257. Min Act: -0.1700
Data Index: 1475561 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0049. Min Range: -3.0049
Max Act: 2.9257. Min Act: -0.1700
Data Index: 1488545 (Python Code)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19