Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 303 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.5785. Min Act: -0.1700
Data Index: 240859 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.3910. Min Act: -0.1700
Data Index: 854281 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1410. Min Act: -0.1700
Data Index: 365884 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.2348. Min Act: -0.1700
Data Index: 1461106 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1723. Min Act: -0.1700
Data Index: 723171 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.0473. Min Act: -0.1700
Data Index: 905051 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1723. Min Act: -0.1700
Data Index: 361944 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.2660. Min Act: -0.1700
Data Index: 1118455 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1098. Min Act: -0.1700
Data Index: 1168931 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.2348. Min Act: -0.1700
Data Index: 1393596 (Python Code)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.0473. Min Act: -0.1700
Data Index: 345472 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1098. Min Act: -0.1700
Data Index: 675655 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1410. Min Act: -0.1700
Data Index: 1454883 (Python Code)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.0160. Min Act: -0.1700
Data Index: 1220726 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1723. Min Act: -0.1700
Data Index: 1641144 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1098. Min Act: -0.1700
Data Index: 1448061 (Python Code)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.0160. Min Act: -0.1700
Data Index: 1595014 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1098. Min Act: -0.1700
Data Index: 1626404 (Python Code)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1098. Min Act: -0.1700
Data Index: 1623495 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5785. Min Range: -6.5785
Max Act: 6.1723. Min Act: -0.1700
Data Index: 930803 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19