Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3593 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1655. Min Range: -6.1655
Max Act: 6.1655. Min Act: -0.1700
Data Index: 4599594 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1655. Min Range: -6.1655
Max Act: 6.0405. Min Act: -0.1700
Data Index: 184496 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1655. Min Range: -6.1655
Max Act: 6.0093. Min Act: -0.1700
Data Index: 6109991 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.9780. Min Act: -0.1700
Data Index: 5827886 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.9780. Min Act: -0.1700
Data Index: 473362 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.9780. Min Act: -0.1700
Data Index: 7544388 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.9155. Min Act: -0.1700
Data Index: 2005380 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.9155. Min Act: -0.1700
Data Index: 3065075 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.9155. Min Act: -0.1700
Data Index: 2068701 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.8843. Min Act: -0.1700
Data Index: 2055353 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.8530. Min Act: -0.1700
Data Index: 6431965 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.8218. Min Act: -0.1700
Data Index: 3166271 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.8218. Min Act: -0.1700
Data Index: 2177652 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.7905. Min Act: -0.1700
Data Index: 6107999 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.7905. Min Act: -0.1700
Data Index: 7988039 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.7905. Min Act: -0.1700
Data Index: 7638390 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.7905. Min Act: -0.1700
Data Index: 7281058 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.7905. Min Act: -0.1700
Data Index: 3749531 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.7593. Min Act: -0.1700
Data Index: 1070760 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1655. Min Range: -6.1655
Max Act: 5.7593. Min Act: -0.1700
Data Index: 2292658 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19