Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1891 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.2938. Min Act: -0.1700
Data Index: 794722 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.2624. Min Act: -0.1700
Data Index: 771066 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.2467. Min Act: -0.1700
Data Index: 1035007 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.2152. Min Act: -0.1700
Data Index: 1020629 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.2152. Min Act: -0.1700
Data Index: 784904 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.2152. Min Act: -0.1700
Data Index: 1205300 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.2152. Min Act: -0.1700
Data Index: 132274 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1995. Min Act: -0.1700
Data Index: 1000423 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1837. Min Act: -0.1700
Data Index: 166193 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1837. Min Act: -0.1700
Data Index: 51023 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1995. Min Act: -0.1700
Data Index: 1161932 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1680. Min Act: -0.1700
Data Index: 887664 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1837. Min Act: -0.1700
Data Index: 101780 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1680. Min Act: -0.1700
Data Index: 399405 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1523. Min Act: -0.1700
Data Index: 1025835 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1523. Min Act: -0.1700
Data Index: 804252 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1680. Min Act: -0.1700
Data Index: 1074254 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1523. Min Act: -0.1700
Data Index: 722837 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1523. Min Act: -0.1700
Data Index: 9772 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2938. Min Range: -3.2938
Max Act: 3.1050. Min Act: -0.1700
Data Index: 603002 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19