Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2012 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0998. Min Act: -0.1700
Data Index: 878912 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0685. Min Act: -0.1700
Data Index: 97319 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0998. Min Act: -0.1700
Data Index: 636372 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0373. Min Act: -0.1700
Data Index: 1121390 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0685. Min Act: -0.1700
Data Index: 1135306 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9435. Min Act: -0.1700
Data Index: 1295492 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0373. Min Act: -0.1700
Data Index: 703870 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9747. Min Act: -0.1700
Data Index: 1028446 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0060. Min Act: -0.1700
Data Index: 700101 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0373. Min Act: -0.1700
Data Index: 248519 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9747. Min Act: -0.1700
Data Index: 925276 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9435. Min Act: -0.1700
Data Index: 1341747 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9747. Min Act: -0.1700
Data Index: 1046313 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0060. Min Act: -0.1700
Data Index: 796082 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0998. Min Range: -4.0998
Max Act: 4.0060. Min Act: -0.1700
Data Index: 132609 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9435. Min Act: -0.1700
Data Index: 1046496 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9435. Min Act: -0.1700
Data Index: 606286 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9747. Min Act: -0.1700
Data Index: 1287747 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9122. Min Act: -0.1700
Data Index: 774043 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0998. Min Range: -4.0998
Max Act: 3.9122. Min Act: -0.1700
Data Index: 1045957 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19