Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1895 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.9309. Min Act: -0.1700
Data Index: 162562 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.9150. Min Act: -0.1700
Data Index: 34121 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.8515. Min Act: -0.1700
Data Index: 381307 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.8197. Min Act: -0.1700
Data Index: 888088 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.8197. Min Act: -0.1700
Data Index: 1052884 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7879. Min Act: -0.1700
Data Index: 497069 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7879. Min Act: -0.1700
Data Index: 943275 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7400. Min Act: -0.1700
Data Index: 980843 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7081. Min Act: -0.1700
Data Index: 208778 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7560. Min Act: -0.1700
Data Index: 350525 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7400. Min Act: -0.1700
Data Index: 588061 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7400. Min Act: -0.1700
Data Index: 1179888 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7081. Min Act: -0.1700
Data Index: 259612 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7240. Min Act: -0.1700
Data Index: 710845 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7240. Min Act: -0.1700
Data Index: 1517936 (Python Code)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.6760. Min Act: -0.1700
Data Index: 1598816 (Python Code)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7240. Min Act: -0.1700
Data Index: 14147 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7081. Min Act: -0.1700
Data Index: 1192416 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.7081. Min Act: -0.1700
Data Index: 208049 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9309. Min Range: -2.9309
Max Act: 2.6921. Min Act: -0.1700
Data Index: 872251 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19