Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 33 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.2925. Min Act: -0.1700
Data Index: 1056544 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.2760. Min Act: -0.1700
Data Index: 666018 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.2265. Min Act: -0.1700
Data Index: 475776 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.2265. Min Act: -0.1700
Data Index: 322234 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.2100. Min Act: -0.1700
Data Index: 720797 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.1601. Min Act: -0.1700
Data Index: 1180093 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.1601. Min Act: -0.1700
Data Index: 184056 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.1435. Min Act: -0.1700
Data Index: 780483 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.1268. Min Act: -0.1700
Data Index: 1038750 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0934. Min Act: -0.1700
Data Index: 1099672 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.1101. Min Act: -0.1700
Data Index: 320289 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0766. Min Act: -0.1700
Data Index: 71875 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0766. Min Act: -0.1700
Data Index: 537591 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0766. Min Act: -0.1700
Data Index: 920237 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0766. Min Act: -0.1700
Data Index: 808425 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0598. Min Act: -0.1700
Data Index: 343998 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0598. Min Act: -0.1700
Data Index: 393393 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0262. Min Act: -0.1700
Data Index: 315938 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0430. Min Act: -0.1700
Data Index: 390450 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2925. Min Range: -2.2925
Max Act: 2.0430. Min Act: -0.1700
Data Index: 787036 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19