Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1403 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.6046. Min Act: -0.1700
Data Index: 349660 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.5421. Min Act: -0.1700
Data Index: 529509 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.5421. Min Act: -0.1700
Data Index: 272278 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4796. Min Act: -0.1700
Data Index: 634924 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4796. Min Act: -0.1700
Data Index: 502419 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.5109. Min Act: -0.1700
Data Index: 1285149 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4796. Min Act: -0.1700
Data Index: 609551 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4484. Min Act: -0.1700
Data Index: 1246947 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4484. Min Act: -0.1700
Data Index: 936807 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4171. Min Act: -0.1700
Data Index: 669873 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4796. Min Act: -0.1700
Data Index: 789252 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4171. Min Act: -0.1700
Data Index: 1610483 (Python Code)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4171. Min Act: -0.1700
Data Index: 1412479 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4171. Min Act: -0.1700
Data Index: 213664 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.3859. Min Act: -0.1700
Data Index: 212641 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.4171. Min Act: -0.1700
Data Index: 215947 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.3859. Min Act: -0.1700
Data Index: 709123 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.3859. Min Act: -0.1700
Data Index: 651084 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.3859. Min Act: -0.1700
Data Index: 74661 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6046. Min Range: -4.6046
Max Act: 4.3859. Min Act: -0.1700
Data Index: 747719 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19