Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1530 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.7108. Min Act: -0.1700
Data Index: 544493 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6948. Min Act: -0.1700
Data Index: 27696 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6788. Min Act: -0.1700
Data Index: 1496844 (Python Code)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6948. Min Act: -0.1700
Data Index: 1034598 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6948. Min Act: -0.1700
Data Index: 1555795 (Python Code)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6788. Min Act: -0.1700
Data Index: 1519101 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6627. Min Act: -0.1700
Data Index: 440886 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6467. Min Act: -0.1700
Data Index: 1623245 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6788. Min Act: -0.1700
Data Index: 1541503 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6788. Min Act: -0.1700
Data Index: 1410544 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6788. Min Act: -0.1700
Data Index: 1532133 (Python Code)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6627. Min Act: -0.1700
Data Index: 1609753 (Python Code)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6627. Min Act: -0.1700
Data Index: 1645117 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6627. Min Act: -0.1700
Data Index: 886976 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6627. Min Act: -0.1700
Data Index: 156513 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6627. Min Act: -0.1700
Data Index: 330960 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6467. Min Act: -0.1700
Data Index: 1534606 (Python Code)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6467. Min Act: -0.1700
Data Index: 1516153 (Python Code)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6467. Min Act: -0.1700
Data Index: 558756 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7108. Min Range: -2.7108
Max Act: 2.6306. Min Act: -0.1700
Data Index: 1130784 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19