Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1602 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.8065. Min Act: -0.1700
Data Index: 941209 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.7753. Min Act: -0.1700
Data Index: 1249112 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.7440. Min Act: -0.1700
Data Index: 758887 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6815. Min Act: -0.1700
Data Index: 536501 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6815. Min Act: -0.1700
Data Index: 114076 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6503. Min Act: -0.1700
Data Index: 1097834 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.7128. Min Act: -0.1700
Data Index: 1249369 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6815. Min Act: -0.1700
Data Index: 832754 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.7128. Min Act: -0.1700
Data Index: 178605 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6190. Min Act: -0.1700
Data Index: 987454 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6815. Min Act: -0.1700
Data Index: 573674 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.7128. Min Act: -0.1700
Data Index: 517363 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6815. Min Act: -0.1700
Data Index: 61560 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6190. Min Act: -0.1700
Data Index: 1244088 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6503. Min Act: -0.1700
Data Index: 709309 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6503. Min Act: -0.1700
Data Index: 675842 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6503. Min Act: -0.1700
Data Index: 527646 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6190. Min Act: -0.1700
Data Index: 801551 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.5878. Min Act: -0.1700
Data Index: 1223500 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8065. Min Range: -4.8065
Max Act: 4.6190. Min Act: -0.1700
Data Index: 3845 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19