Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 11 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.9533. Min Act: -0.1700
Data Index: 1262232 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.9057. Min Act: -0.1700
Data Index: 1023320 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.8422. Min Act: -0.1700
Data Index: 784275 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.8263. Min Act: -0.1700
Data Index: 733703 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7945. Min Act: -0.1700
Data Index: 1199155 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7945. Min Act: -0.1700
Data Index: 1279193 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7785. Min Act: -0.1700
Data Index: 694268 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7626. Min Act: -0.1700
Data Index: 762694 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7785. Min Act: -0.1700
Data Index: 120501 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7626. Min Act: -0.1700
Data Index: 1235653 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7307. Min Act: -0.1700
Data Index: 654497 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7466. Min Act: -0.1700
Data Index: 65087 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7466. Min Act: -0.1700
Data Index: 1329737 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7466. Min Act: -0.1700
Data Index: 676732 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7307. Min Act: -0.1700
Data Index: 152824 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7307. Min Act: -0.1700
Data Index: 1246566 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.7307. Min Act: -0.1700
Data Index: 66400 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.6987. Min Act: -0.1700
Data Index: 1536525 (Python Code)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.6987. Min Act: -0.1700
Data Index: 1637916 (Python Code)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9533. Min Range: -2.9533
Max Act: 2.6987. Min Act: -0.1700
Data Index: 1070919 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19