Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.8115. Min Act: -0.1700
Data Index: 581022 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.7478. Min Act: -0.1700
Data Index: 210424 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6838. Min Act: -0.1700
Data Index: 1193690 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6838. Min Act: -0.1700
Data Index: 735064 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6838. Min Act: -0.1700
Data Index: 1185291 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6838. Min Act: -0.1700
Data Index: 694816 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6838. Min Act: -0.1700
Data Index: 439707 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6838. Min Act: -0.1700
Data Index: 666779 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6838. Min Act: -0.1700
Data Index: 1282042 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6838. Min Act: -0.1700
Data Index: 486868 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6196. Min Act: -0.1700
Data Index: 989066 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.6196. Min Act: -0.1700
Data Index: 1038582 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.5874. Min Act: -0.1700
Data Index: 128595 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.5874. Min Act: -0.1700
Data Index: 829647 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.5713. Min Act: -0.1700
Data Index: 201990 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.5391. Min Act: -0.1700
Data Index: 372163 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.5391. Min Act: -0.1700
Data Index: 210983 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.5391. Min Act: -0.1700
Data Index: 1001242 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.5552. Min Act: -0.1700
Data Index: 149581 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8115. Min Range: -2.8115
Max Act: 2.5391. Min Act: -0.1700
Data Index: 1217211 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19