Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2765 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.4478. Min Act: -0.1700
Data Index: 2975397 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.4166. Min Act: -0.1700
Data Index: 3943445 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.3228. Min Act: -0.1700
Data Index: 3068386 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.1666. Min Act: -0.1700
Data Index: 365843 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.1666. Min Act: -0.1700
Data Index: 2527984 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.1041. Min Act: -0.1700
Data Index: 5979937 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.1041. Min Act: -0.1700
Data Index: 5935423 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.0728. Min Act: -0.1700
Data Index: 3168056 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.0728. Min Act: -0.1700
Data Index: 794451 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.0728. Min Act: -0.1700
Data Index: 285198 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.0103. Min Act: -0.1700
Data Index: 8529442 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.0103. Min Act: -0.1700
Data Index: 6742723 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4478. Min Range: -6.4478
Max Act: 6.0103. Min Act: -0.1700
Data Index: 6131048 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4478. Min Range: -6.4478
Max Act: 5.9791. Min Act: -0.1700
Data Index: 3980279 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4478. Min Range: -6.4478
Max Act: 5.9791. Min Act: -0.1700
Data Index: 3160532 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4478. Min Range: -6.4478
Max Act: 5.9791. Min Act: -0.1700
Data Index: 995525 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4478. Min Range: -6.4478
Max Act: 5.9478. Min Act: -0.1700
Data Index: 5547708 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4478. Min Range: -6.4478
Max Act: 5.9166. Min Act: -0.1700
Data Index: 378354 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4478. Min Range: -6.4478
Max Act: 5.8853. Min Act: -0.1700
Data Index: 4202302 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4478. Min Range: -6.4478
Max Act: 5.8853. Min Act: -0.1700
Data Index: 4920279 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19