Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2671 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0819. Min Range: -6.0819
Max Act: 6.0819. Min Act: -0.1700
Data Index: 1018602 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0819. Min Range: -6.0819
Max Act: 6.0819. Min Act: -0.1700
Data Index: 7181493 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0819. Min Range: -6.0819
Max Act: 6.0507. Min Act: -0.1700
Data Index: 1285057 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.9569. Min Act: -0.1700
Data Index: 218019 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.8007. Min Act: -0.1700
Data Index: 4241672 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.6132. Min Act: -0.1700
Data Index: 2421195 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.6132. Min Act: -0.1700
Data Index: 74785 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.6132. Min Act: -0.1700
Data Index: 7211809 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.6132. Min Act: -0.1700
Data Index: 2285107 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.6132. Min Act: -0.1700
Data Index: 586638 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.5819. Min Act: -0.1700
Data Index: 2356735 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.5507. Min Act: -0.1700
Data Index: 735452 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.5819. Min Act: -0.1700
Data Index: 7055065 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.5507. Min Act: -0.1700
Data Index: 3632569 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.5194. Min Act: -0.1700
Data Index: 6346026 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.4882. Min Act: -0.1700
Data Index: 8254386 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.4882. Min Act: -0.1700
Data Index: 6093437 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.4882. Min Act: -0.1700
Data Index: 1444703 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.4882. Min Act: -0.1700
Data Index: 1257186 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0819. Min Range: -6.0819
Max Act: 5.4569. Min Act: -0.1700
Data Index: 5355685 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19