Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6384 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.7218. Min Act: -0.1700
Data Index: 7511585 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.6593. Min Act: -0.1700
Data Index: 1417953 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5968. Min Act: -0.1700
Data Index: 7627716 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5656. Min Act: -0.1700
Data Index: 3249463 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5656. Min Act: -0.1700
Data Index: 4467994 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5031. Min Act: -0.1700
Data Index: 3271688 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4718. Min Act: -0.1700
Data Index: 700130 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4406. Min Act: -0.1700
Data Index: 7899979 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4406. Min Act: -0.1700
Data Index: 6147553 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4093. Min Act: -0.1700
Data Index: 4237770 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4093. Min Act: -0.1700
Data Index: 6826445 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.3781. Min Act: -0.1700
Data Index: 903040 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.3781. Min Act: -0.1700
Data Index: 5624611 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.3468. Min Act: -0.1700
Data Index: 1973523 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.3156. Min Act: -0.1700
Data Index: 4859540 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.2843. Min Act: -0.1700
Data Index: 6203309 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.2843. Min Act: -0.1700
Data Index: 2934895 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.2531. Min Act: -0.1700
Data Index: 6068312 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.2218. Min Act: -0.1700
Data Index: 6020154 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.2218. Min Act: -0.1700
Data Index: 4305625 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19