Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 159 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0590. Min Act: -0.1700
Data Index: 812694 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0748. Min Act: -0.1700
Data Index: 1276245 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0590. Min Act: -0.1700
Data Index: 1246779 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0590. Min Act: -0.1700
Data Index: 231990 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0432. Min Act: -0.1700
Data Index: 1160254 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0432. Min Act: -0.1700
Data Index: 786248 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0274. Min Act: -0.1700
Data Index: 129790 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0432. Min Act: -0.1700
Data Index: 1183261 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0274. Min Act: -0.1700
Data Index: 637977 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0116. Min Act: -0.1700
Data Index: 60695 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0274. Min Act: -0.1700
Data Index: 1176071 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0116. Min Act: -0.1700
Data Index: 673101 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0748. Min Range: -3.0748
Max Act: 2.9958. Min Act: -0.1700
Data Index: 397679 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0748. Min Range: -3.0748
Max Act: 3.0116. Min Act: -0.1700
Data Index: 351029 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0748. Min Range: -3.0748
Max Act: 2.9958. Min Act: -0.1700
Data Index: 649913 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0748. Min Range: -3.0748
Max Act: 2.9958. Min Act: -0.1700
Data Index: 606031 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0748. Min Range: -3.0748
Max Act: 2.9958. Min Act: -0.1700
Data Index: 1101066 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0748. Min Range: -3.0748
Max Act: 2.9958. Min Act: -0.1700
Data Index: 175750 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0748. Min Range: -3.0748
Max Act: 2.9958. Min Act: -0.1700
Data Index: 901331 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0748. Min Range: -3.0748
Max Act: 2.9800. Min Act: -0.1700
Data Index: 1044983 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19