Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1933 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0726. Min Range: -4.0726
Max Act: 4.0726. Min Act: -0.1700
Data Index: 768681 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0726. Min Range: -4.0726
Max Act: 4.0413. Min Act: -0.1700
Data Index: 444666 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0726. Min Range: -4.0726
Max Act: 4.0413. Min Act: -0.1700
Data Index: 195556 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0726. Min Range: -4.0726
Max Act: 4.0100. Min Act: -0.1700
Data Index: 1187445 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0726. Min Range: -4.0726
Max Act: 4.0100. Min Act: -0.1700
Data Index: 486030 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9788. Min Act: -0.1700
Data Index: 506513 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9788. Min Act: -0.1700
Data Index: 311023 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9788. Min Act: -0.1700
Data Index: 477334 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9162. Min Act: -0.1700
Data Index: 1501546 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9475. Min Act: -0.1700
Data Index: 285002 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9162. Min Act: -0.1700
Data Index: 357435 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.8850. Min Act: -0.1700
Data Index: 1416967 (Python Code)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9162. Min Act: -0.1700
Data Index: 1543053 (Python Code)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.8850. Min Act: -0.1700
Data Index: 1633238 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9162. Min Act: -0.1700
Data Index: 1483525 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9162. Min Act: -0.1700
Data Index: 1395072 (Python Code)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.9162. Min Act: -0.1700
Data Index: 584985 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.8850. Min Act: -0.1700
Data Index: 1569977 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.8850. Min Act: -0.1700
Data Index: 1511508 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0726. Min Range: -4.0726
Max Act: 3.8537. Min Act: -0.1700
Data Index: 1407139 (Python Code)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19