Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1029 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.8614. Min Act: -0.1700
Data Index: 230874 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.8614. Min Act: -0.1700
Data Index: 1431524 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.8455. Min Act: -0.1700
Data Index: 1469107 (Python Code)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.8296. Min Act: -0.1700
Data Index: 1348780 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.8296. Min Act: -0.1700
Data Index: 377646 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.8137. Min Act: -0.1700
Data Index: 763266 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.8137. Min Act: -0.1700
Data Index: 517827 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7819. Min Act: -0.1700
Data Index: 103042 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7978. Min Act: -0.1700
Data Index: 1236767 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7978. Min Act: -0.1700
Data Index: 78578 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7978. Min Act: -0.1700
Data Index: 1057577 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7819. Min Act: -0.1700
Data Index: 79001 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7659. Min Act: -0.1700
Data Index: 656977 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7819. Min Act: -0.1700
Data Index: 848156 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7819. Min Act: -0.1700
Data Index: 754092 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7819. Min Act: -0.1700
Data Index: 1246383 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7819. Min Act: -0.1700
Data Index: 720402 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7819. Min Act: -0.1700
Data Index: 992374 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7659. Min Act: -0.1700
Data Index: 121088 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8614. Min Range: -2.8614
Max Act: 2.7659. Min Act: -0.1700
Data Index: 941006 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19