Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 104 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.5415. Min Act: -0.1700
Data Index: 1074781 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.3791. Min Act: -0.1700
Data Index: 1137220 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.3464. Min Act: -0.1700
Data Index: 1114372 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.3464. Min Act: -0.1700
Data Index: 994666 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.3136. Min Act: -0.1700
Data Index: 797066 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.3300. Min Act: -0.1700
Data Index: 673046 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.3136. Min Act: -0.1700
Data Index: 883812 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.3136. Min Act: -0.1700
Data Index: 910489 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2971. Min Act: -0.1700
Data Index: 257433 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2971. Min Act: -0.1700
Data Index: 611466 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.3136. Min Act: -0.1700
Data Index: 286581 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2971. Min Act: -0.1700
Data Index: 1258214 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2971. Min Act: -0.1700
Data Index: 6782 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2971. Min Act: -0.1700
Data Index: 437916 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2971. Min Act: -0.1700
Data Index: 280120 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2642. Min Act: -0.1700
Data Index: 137085 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2807. Min Act: -0.1700
Data Index: 24158 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2807. Min Act: -0.1700
Data Index: 428197 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2807. Min Act: -0.1700
Data Index: 352654 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5415. Min Range: -2.5415
Max Act: 2.2807. Min Act: -0.1700
Data Index: 191358 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19