Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1977 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0745. Min Range: -3.0745
Max Act: 3.0745. Min Act: -0.1700
Data Index: 299656 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.9797. Min Act: -0.1700
Data Index: 213387 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.9639. Min Act: -0.1700
Data Index: 111787 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.9481. Min Act: -0.1700
Data Index: 226613 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.9639. Min Act: -0.1700
Data Index: 292688 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.9322. Min Act: -0.1700
Data Index: 83551 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8846. Min Act: -0.1700
Data Index: 1207710 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8688. Min Act: -0.1700
Data Index: 751103 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.9005. Min Act: -0.1700
Data Index: 524654 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8688. Min Act: -0.1700
Data Index: 400134 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8688. Min Act: -0.1700
Data Index: 960324 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8846. Min Act: -0.1700
Data Index: 989055 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8688. Min Act: -0.1700
Data Index: 1227635 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8688. Min Act: -0.1700
Data Index: 426902 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8529. Min Act: -0.1700
Data Index: 155977 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8529. Min Act: -0.1700
Data Index: 771830 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8529. Min Act: -0.1700
Data Index: 1060277 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8370. Min Act: -0.1700
Data Index: 1204960 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8529. Min Act: -0.1700
Data Index: 928192 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0745. Min Range: -3.0745
Max Act: 2.8529. Min Act: -0.1700
Data Index: 1213315 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19