Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6375 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3606. Min Range: -6.3606
Max Act: 6.3606. Min Act: -0.1700
Data Index: 3326747 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3606. Min Range: -6.3606
Max Act: 6.0794. Min Act: -0.1700
Data Index: 1446953 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.9544. Min Act: -0.1700
Data Index: 5768304 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.8919. Min Act: -0.1700
Data Index: 5286312 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.8606. Min Act: -0.1700
Data Index: 3162951 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.7669. Min Act: -0.1700
Data Index: 4727001 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.7356. Min Act: -0.1700
Data Index: 2994445 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.7669. Min Act: -0.1700
Data Index: 1888077 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.7356. Min Act: -0.1700
Data Index: 6975676 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.7669. Min Act: -0.1700
Data Index: 1454335 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.7044. Min Act: -0.1700
Data Index: 3972865 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.7044. Min Act: -0.1700
Data Index: 3647291 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.6731. Min Act: -0.1700
Data Index: 5100606 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.6106. Min Act: -0.1700
Data Index: 8455504 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.6419. Min Act: -0.1700
Data Index: 2251668 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.6419. Min Act: -0.1700
Data Index: 6058684 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.6419. Min Act: -0.1700
Data Index: 4701409 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.6106. Min Act: -0.1700
Data Index: 8355107 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.6106. Min Act: -0.1700
Data Index: 8388957 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3606. Min Range: -6.3606
Max Act: 5.6106. Min Act: -0.1700
Data Index: 7813249 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19