Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 470 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.8941. Min Act: -0.1700
Data Index: 1644002 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.8305. Min Act: -0.1700
Data Index: 1504730 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.8464. Min Act: -0.1700
Data Index: 1601788 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.8146. Min Act: -0.1700
Data Index: 1384300 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7668. Min Act: -0.1700
Data Index: 566533 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7509. Min Act: -0.1700
Data Index: 803683 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7349. Min Act: -0.1700
Data Index: 1412872 (Python Code)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7189. Min Act: -0.1700
Data Index: 1596612 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7189. Min Act: -0.1700
Data Index: 1406571 (Python Code)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7189. Min Act: -0.1700
Data Index: 1471096 (Python Code)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7029. Min Act: -0.1700
Data Index: 280899 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.6869. Min Act: -0.1700
Data Index: 1603931 (Python Code)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.6869. Min Act: -0.1700
Data Index: 1552039 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7029. Min Act: -0.1700
Data Index: 1429326 (Python Code)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.6869. Min Act: -0.1700
Data Index: 1129053 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.6869. Min Act: -0.1700
Data Index: 1590624 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.6709. Min Act: -0.1700
Data Index: 1657094 (Python Code)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7029. Min Act: -0.1700
Data Index: 1433341 (Python Code)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.7029. Min Act: -0.1700
Data Index: 1563026 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8941. Min Range: -2.8941
Max Act: 2.6869. Min Act: -0.1700
Data Index: 1459098 (Python Code)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19