Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6255 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.5808. Min Act: -0.1700
Data Index: 5238216 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.4870. Min Act: -0.1700
Data Index: 6823104 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.4870. Min Act: -0.1700
Data Index: 4850134 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.4245. Min Act: -0.1700
Data Index: 4218520 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.4245. Min Act: -0.1700
Data Index: 4513674 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.3620. Min Act: -0.1700
Data Index: 1080648 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.3933. Min Act: -0.1700
Data Index: 878953 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.3308. Min Act: -0.1700
Data Index: 7634136 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.3308. Min Act: -0.1700
Data Index: 2840400 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.3308. Min Act: -0.1700
Data Index: 8825537 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.3308. Min Act: -0.1700
Data Index: 4905166 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.2995. Min Act: -0.1700
Data Index: 1080647 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.2995. Min Act: -0.1700
Data Index: 4748632 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.3308. Min Act: -0.1700
Data Index: 4809937 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.2370. Min Act: -0.1700
Data Index: 4605768 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.2683. Min Act: -0.1700
Data Index: 1707680 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.2683. Min Act: -0.1700
Data Index: 3539233 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.2370. Min Act: -0.1700
Data Index: 975204 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.2370. Min Act: -0.1700
Data Index: 3310174 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5808. Min Range: -4.5808
Max Act: 4.2683. Min Act: -0.1700
Data Index: 7693004 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19