Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.7011. Min Act: -0.1700
Data Index: 529416 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.4511. Min Act: -0.1700
Data Index: 7969820 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.4511. Min Act: -0.1700
Data Index: 6663812 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.4199. Min Act: -0.1700
Data Index: 8210533 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3261. Min Act: -0.1700
Data Index: 8499623 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3261. Min Act: -0.1700
Data Index: 3713934 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2949. Min Act: -0.1700
Data Index: 3344184 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3261. Min Act: -0.1700
Data Index: 1035911 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3261. Min Act: -0.1700
Data Index: 102940 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3574. Min Act: -0.1700
Data Index: 967690 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2949. Min Act: -0.1700
Data Index: 6144249 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2949. Min Act: -0.1700
Data Index: 6813986 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2636. Min Act: -0.1700
Data Index: 3778483 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2949. Min Act: -0.1700
Data Index: 6600376 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2324. Min Act: -0.1700
Data Index: 3768651 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2324. Min Act: -0.1700
Data Index: 6614059 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2324. Min Act: -0.1700
Data Index: 127782 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2324. Min Act: -0.1700
Data Index: 5188726 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2324. Min Act: -0.1700
Data Index: 4362483 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2324. Min Act: -0.1700
Data Index: 2276521 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19