Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 200 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.9629. Min Act: -0.1700
Data Index: 1098356 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.7129. Min Act: -0.1700
Data Index: 7448 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.6504. Min Act: -0.1700
Data Index: 721698 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.7441. Min Act: -0.1700
Data Index: 1231691 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5879. Min Act: -0.1700
Data Index: 130774 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5879. Min Act: -0.1700
Data Index: 587545 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5879. Min Act: -0.1700
Data Index: 987368 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5879. Min Act: -0.1700
Data Index: 1141168 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5566. Min Act: -0.1700
Data Index: 300002 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5879. Min Act: -0.1700
Data Index: 926522 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5254. Min Act: -0.1700
Data Index: 1179654 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.4941. Min Act: -0.1700
Data Index: 412984 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5254. Min Act: -0.1700
Data Index: 212898 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.4941. Min Act: -0.1700
Data Index: 386677 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5254. Min Act: -0.1700
Data Index: 1234845 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.4941. Min Act: -0.1700
Data Index: 1067810 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5254. Min Act: -0.1700
Data Index: 1052974 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5566. Min Act: -0.1700
Data Index: 667520 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.4941. Min Act: -0.1700
Data Index: 975867 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9629. Min Range: -4.9629
Max Act: 4.5254. Min Act: -0.1700
Data Index: 289935 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19