Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1033 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0907. Min Range: -3.0907
Max Act: 3.0907. Min Act: -0.1700
Data Index: 7102969 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0907. Min Range: -3.0907
Max Act: 3.0592. Min Act: -0.1700
Data Index: 5017634 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9802. Min Act: -0.1700
Data Index: 2368499 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9960. Min Act: -0.1700
Data Index: 6720627 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9960. Min Act: -0.1700
Data Index: 1621174 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9327. Min Act: -0.1700
Data Index: 100381 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9486. Min Act: -0.1700
Data Index: 5250521 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9169. Min Act: -0.1700
Data Index: 2939864 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9010. Min Act: -0.1700
Data Index: 1185962 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9169. Min Act: -0.1700
Data Index: 4653669 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9169. Min Act: -0.1700
Data Index: 8205444 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9010. Min Act: -0.1700
Data Index: 4502263 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.8852. Min Act: -0.1700
Data Index: 3165891 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.8852. Min Act: -0.1700
Data Index: 2718349 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.9010. Min Act: -0.1700
Data Index: 4105450 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.8852. Min Act: -0.1700
Data Index: 438638 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.8693. Min Act: -0.1700
Data Index: 4418764 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.8693. Min Act: -0.1700
Data Index: 3864651 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.8693. Min Act: -0.1700
Data Index: 1203561 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0907. Min Range: -3.0907
Max Act: 2.8693. Min Act: -0.1700
Data Index: 7101252 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19