Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 7 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.6039. Min Act: -0.1700
Data Index: 33642 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.6039. Min Act: -0.1700
Data Index: 1040806 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5878. Min Act: -0.1700
Data Index: 489902 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5394. Min Act: -0.1700
Data Index: 962980 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5394. Min Act: -0.1700
Data Index: 1246836 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5394. Min Act: -0.1700
Data Index: 1114897 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5071. Min Act: -0.1700
Data Index: 1203901 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5071. Min Act: -0.1700
Data Index: 189661 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5071. Min Act: -0.1700
Data Index: 992144 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5071. Min Act: -0.1700
Data Index: 1014944 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.5071. Min Act: -0.1700
Data Index: 70190 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4909. Min Act: -0.1700
Data Index: 827489 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4909. Min Act: -0.1700
Data Index: 64013 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4909. Min Act: -0.1700
Data Index: 1271276 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4747. Min Act: -0.1700
Data Index: 1102366 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4747. Min Act: -0.1700
Data Index: 506982 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4747. Min Act: -0.1700
Data Index: 228924 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4747. Min Act: -0.1700
Data Index: 582828 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4747. Min Act: -0.1700
Data Index: 670318 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6039. Min Range: -2.6039
Max Act: 2.4747. Min Act: -0.1700
Data Index: 171677 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19