Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1925 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7793. Min Act: -0.1700
Data Index: 77734 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7633. Min Act: -0.1700
Data Index: 517241 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7633. Min Act: -0.1700
Data Index: 754901 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7314. Min Act: -0.1700
Data Index: 1221068 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7474. Min Act: -0.1700
Data Index: 910158 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7314. Min Act: -0.1700
Data Index: 1309687 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7154. Min Act: -0.1700
Data Index: 38067 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7154. Min Act: -0.1700
Data Index: 314718 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7154. Min Act: -0.1700
Data Index: 1301540 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.7154. Min Act: -0.1700
Data Index: 919757 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6994. Min Act: -0.1700
Data Index: 248007 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6834. Min Act: -0.1700
Data Index: 183605 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6994. Min Act: -0.1700
Data Index: 1284193 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6994. Min Act: -0.1700
Data Index: 332744 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6994. Min Act: -0.1700
Data Index: 885836 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6834. Min Act: -0.1700
Data Index: 497457 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6994. Min Act: -0.1700
Data Index: 154454 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1120919 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6834. Min Act: -0.1700
Data Index: 1011967 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7793. Min Range: -2.7793
Max Act: 2.6994. Min Act: -0.1700
Data Index: 944779 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19