Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4637. Min Range: -8.4637
Max Act: 8.4637. Min Act: -0.1700
Data Index: 596654 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4637. Min Range: -8.4637
Max Act: 8.4637. Min Act: -0.1700
Data Index: 7163588 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.8387. Min Act: -0.1700
Data Index: 7334428 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.8387. Min Act: -0.1700
Data Index: 352673 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.7762. Min Act: -0.1700
Data Index: 4132996 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.7762. Min Act: -0.1700
Data Index: 3861859 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.7137. Min Act: -0.1700
Data Index: 6978169 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.6512. Min Act: -0.1700
Data Index: 7837723 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.5887. Min Act: -0.1700
Data Index: 965411 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.5887. Min Act: -0.1700
Data Index: 5980338 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.5887. Min Act: -0.1700
Data Index: 7314595 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.5262. Min Act: -0.1700
Data Index: 7313790 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.5262. Min Act: -0.1700
Data Index: 7692594 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.5887. Min Act: -0.1700
Data Index: 2684243 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.4949. Min Act: -0.1700
Data Index: 2256769 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.4637. Min Act: -0.1700
Data Index: 6634698 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.4324. Min Act: -0.1700
Data Index: 2754853 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.4324. Min Act: -0.1700
Data Index: 4541082 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.4012. Min Act: -0.1700
Data Index: 6471139 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4637. Min Range: -8.4637
Max Act: 7.4012. Min Act: -0.1700
Data Index: 2311938 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19