Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2043 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.3452. Min Act: -0.1700
Data Index: 275964 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.2514. Min Act: -0.1700
Data Index: 1084152 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.1264. Min Act: -0.1700
Data Index: 7706 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.1576. Min Act: -0.1700
Data Index: 912129 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.1576. Min Act: -0.1700
Data Index: 745530 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.1264. Min Act: -0.1700
Data Index: 905238 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0639. Min Act: -0.1700
Data Index: 282407 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0951. Min Act: -0.1700
Data Index: 535708 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0951. Min Act: -0.1700
Data Index: 935429 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0639. Min Act: -0.1700
Data Index: 685731 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0639. Min Act: -0.1700
Data Index: 886245 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0639. Min Act: -0.1700
Data Index: 407445 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0013. Min Act: -0.1700
Data Index: 20916 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0639. Min Act: -0.1700
Data Index: 869300 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0013. Min Act: -0.1700
Data Index: 1346900 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0013. Min Act: -0.1700
Data Index: 1159913 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3452. Min Range: -4.3452
Max Act: 3.9701. Min Act: -0.1700
Data Index: 938916 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3452. Min Range: -4.3452
Max Act: 4.0013. Min Act: -0.1700
Data Index: 26463 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3452. Min Range: -4.3452
Max Act: 3.9075. Min Act: -0.1700
Data Index: 47434 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3452. Min Range: -4.3452
Max Act: 3.9701. Min Act: -0.1700
Data Index: 1030994 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19