Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4587 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0853. Min Range: -5.0853
Max Act: 5.0853. Min Act: -0.1700
Data Index: 3739214 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.9290. Min Act: -0.1700
Data Index: 8554279 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.8665. Min Act: -0.1700
Data Index: 5881726 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.7103. Min Act: -0.1700
Data Index: 8182018 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.7103. Min Act: -0.1700
Data Index: 4469355 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.7103. Min Act: -0.1700
Data Index: 8032949 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.7103. Min Act: -0.1700
Data Index: 6741164 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6790. Min Act: -0.1700
Data Index: 1906729 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6790. Min Act: -0.1699
Data Index: 2953155 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6790. Min Act: -0.1700
Data Index: 2166747 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6790. Min Act: -0.1700
Data Index: 8101693 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6790. Min Act: -0.1700
Data Index: 402762 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6790. Min Act: -0.1700
Data Index: 6547488 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6790. Min Act: -0.1700
Data Index: 2571863 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6790. Min Act: -0.1700
Data Index: 6013816 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6478. Min Act: -0.1700
Data Index: 243175 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6478. Min Act: -0.1700
Data Index: 2916625 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6478. Min Act: -0.1700
Data Index: 1352502 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6478. Min Act: -0.1700
Data Index: 6419934 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0853. Min Range: -5.0853
Max Act: 4.6478. Min Act: -0.1700
Data Index: 8500428 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19