Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1980 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.8771. Min Act: -0.1700
Data Index: 1425606 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.6896. Min Act: -0.1700
Data Index: 7996740 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.6271. Min Act: -0.1700
Data Index: 3470496 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5021. Min Act: -0.1700
Data Index: 873324 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5021. Min Act: -0.1700
Data Index: 8525608 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.5021. Min Act: -0.1700
Data Index: 5267823 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4708. Min Act: -0.1700
Data Index: 6425313 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4708. Min Act: -0.1700
Data Index: 1262149 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4396. Min Act: -0.1700
Data Index: 7699982 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4396. Min Act: -0.1700
Data Index: 4263152 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4396. Min Act: -0.1700
Data Index: 1674036 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4396. Min Act: -0.1700
Data Index: 3729149 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4083. Min Act: -0.1700
Data Index: 2123368 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.4083. Min Act: -0.1700
Data Index: 655887 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.3458. Min Act: -0.1700
Data Index: 2830016 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.3771. Min Act: -0.1700
Data Index: 229634 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.3771. Min Act: -0.1700
Data Index: 1338781 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.3458. Min Act: -0.1700
Data Index: 6436863 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.3458. Min Act: -0.1700
Data Index: 7515892 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8771. Min Range: -5.8771
Max Act: 5.3458. Min Act: -0.1700
Data Index: 1686504 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19