Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 776 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3434. Min Act: -0.1700
Data Index: 4062421 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3434. Min Act: -0.1700
Data Index: 4288160 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3434. Min Act: -0.1700
Data Index: 4694314 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3434. Min Act: -0.1700
Data Index: 8539109 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3434. Min Act: -0.1700
Data Index: 2827939 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3120. Min Act: -0.1700
Data Index: 8260078 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3120. Min Act: -0.1700
Data Index: 288786 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3120. Min Act: -0.1700
Data Index: 8314991 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3120. Min Act: -0.1700
Data Index: 1167322 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3120. Min Act: -0.1700
Data Index: 5733119 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3120. Min Act: -0.1700
Data Index: 3820993 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.2806. Min Act: -0.1700
Data Index: 818099 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.2806. Min Act: -0.1700
Data Index: 8079620 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.2806. Min Act: -0.1700
Data Index: 3436373 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.2806. Min Act: -0.1700
Data Index: 1986522 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.2806. Min Act: -0.1700
Data Index: 8054144 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.2806. Min Act: -0.1700
Data Index: 8028511 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.2806. Min Act: -0.1700
Data Index: 2832355 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.3120. Min Act: -0.1700
Data Index: 7132778 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3434. Min Range: -3.3434
Max Act: 3.2806. Min Act: -0.1700
Data Index: 5952331 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19