Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2005 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.5056. Min Act: -0.1700
Data Index: 383127 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4732. Min Act: -0.1700
Data Index: 350860 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4407. Min Act: -0.1700
Data Index: 1354922 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4570. Min Act: -0.1700
Data Index: 963467 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4570. Min Act: -0.1700
Data Index: 1103512 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4407. Min Act: -0.1700
Data Index: 1454351 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4407. Min Act: -0.1700
Data Index: 998599 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4407. Min Act: -0.1700
Data Index: 981685 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4407. Min Act: -0.1700
Data Index: 330851 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4244. Min Act: -0.1700
Data Index: 814742 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4244. Min Act: -0.1700
Data Index: 1640423 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4244. Min Act: -0.1700
Data Index: 743391 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4244. Min Act: -0.1700
Data Index: 82932 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4244. Min Act: -0.1700
Data Index: 462428 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4244. Min Act: -0.1700
Data Index: 632880 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4244. Min Act: -0.1700
Data Index: 17213 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4081. Min Act: -0.1700
Data Index: 508062 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4081. Min Act: -0.1700
Data Index: 167485 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4081. Min Act: -0.1700
Data Index: 565446 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5056. Min Range: -2.5056
Max Act: 2.4081. Min Act: -0.1700
Data Index: 322713 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19