Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.8117. Min Act: -0.1700
Data Index: 895662 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.6554. Min Act: -0.1700
Data Index: 4226895 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.6242. Min Act: -0.1700
Data Index: 2997724 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.4679. Min Act: -0.1700
Data Index: 6447753 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.4367. Min Act: -0.1700
Data Index: 7189737 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.4367. Min Act: -0.1700
Data Index: 7189738 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.4367. Min Act: -0.1700
Data Index: 653248 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.4054. Min Act: -0.1700
Data Index: 3257092 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.3429. Min Act: -0.1700
Data Index: 156741 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.3429. Min Act: -0.1700
Data Index: 4993700 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.3117. Min Act: -0.1700
Data Index: 3757341 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.3117. Min Act: -0.1700
Data Index: 3710831 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.2804. Min Act: -0.1700
Data Index: 1283873 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.2804. Min Act: -0.1700
Data Index: 6747395 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.2492. Min Act: -0.1700
Data Index: 3665568 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.2492. Min Act: -0.1700
Data Index: 1565643 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.2492. Min Act: -0.1700
Data Index: 102918 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.2492. Min Act: -0.1700
Data Index: 5848728 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.1867. Min Act: -0.1700
Data Index: 746327 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8117. Min Range: -7.8117
Max Act: 7.2179. Min Act: -0.1700
Data Index: 7779418 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19