Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2021 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1876. Min Act: -0.1700
Data Index: 617821 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1564. Min Act: -0.1700
Data Index: 512493 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1564. Min Act: -0.1700
Data Index: 1073094 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1564. Min Act: -0.1700
Data Index: 1095915 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1564. Min Act: -0.1700
Data Index: 515330 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1564. Min Act: -0.1700
Data Index: 239082 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1564. Min Act: -0.1700
Data Index: 99078 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 904711 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 148506 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 522547 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 569592 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 585649 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 658858 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.0938. Min Act: -0.1700
Data Index: 1020273 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 349760 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 1214060 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1564. Min Act: -0.1700
Data Index: 429173 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.1251. Min Act: -0.1700
Data Index: 443377 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.0626. Min Act: -0.1700
Data Index: 437942 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1876. Min Range: -4.1876
Max Act: 4.0626. Min Act: -0.1700
Data Index: 439533 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19