Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.3764. Min Act: -0.1700
Data Index: 1930500 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.3139. Min Act: -0.1700
Data Index: 60035 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.2201. Min Act: -0.1700
Data Index: 3238104 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1576. Min Act: -0.1700
Data Index: 8589390 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1264. Min Act: -0.1700
Data Index: 1101874 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1576. Min Act: -0.1700
Data Index: 2737005 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1576. Min Act: -0.1700
Data Index: 7666605 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.1264. Min Act: -0.1700
Data Index: 1328276 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0951. Min Act: -0.1700
Data Index: 2774443 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0951. Min Act: -0.1700
Data Index: 8606552 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0326. Min Act: -0.1700
Data Index: 1755891 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0326. Min Act: -0.1700
Data Index: 8589400 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0014. Min Act: -0.1700
Data Index: 6341049 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0014. Min Act: -0.1700
Data Index: 556637 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0014. Min Act: -0.1700
Data Index: 7883763 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3764. Min Range: -5.3764
Max Act: 4.9701. Min Act: -0.1700
Data Index: 6556117 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3764. Min Range: -5.3764
Max Act: 4.9701. Min Act: -0.1700
Data Index: 1945506 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3764. Min Range: -5.3764
Max Act: 5.0014. Min Act: -0.1700
Data Index: 6496790 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3764. Min Range: -5.3764
Max Act: 4.9076. Min Act: -0.1700
Data Index: 5563568 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3764. Min Range: -5.3764
Max Act: 4.9389. Min Act: -0.1700
Data Index: 2435763 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19