Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0528. Min Range: -6.0528
Max Act: 6.0528. Min Act: -0.1700
Data Index: 4915216 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.6778. Min Act: -0.1700
Data Index: 7740030 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.6466. Min Act: -0.1700
Data Index: 5784428 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.4903. Min Act: -0.1700
Data Index: 5995422 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.4903. Min Act: -0.1700
Data Index: 7965172 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.4278. Min Act: -0.1700
Data Index: 4056824 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.4591. Min Act: -0.1700
Data Index: 1859448 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.4278. Min Act: -0.1700
Data Index: 6820230 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.4278. Min Act: -0.1700
Data Index: 8589299 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.3653. Min Act: -0.1700
Data Index: 7828552 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.3653. Min Act: -0.1700
Data Index: 2215618 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.3653. Min Act: -0.1700
Data Index: 5547686 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.3341. Min Act: -0.1700
Data Index: 6341516 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.3653. Min Act: -0.1700
Data Index: 1416761 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.2716. Min Act: -0.1700
Data Index: 7801410 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.2716. Min Act: -0.1700
Data Index: 87037 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.3028. Min Act: -0.1700
Data Index: 5869769 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.2716. Min Act: -0.1700
Data Index: 1573959 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.2403. Min Act: -0.1700
Data Index: 6289854 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0528. Min Range: -6.0528
Max Act: 5.2403. Min Act: -0.1700
Data Index: 321445 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19