Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2216. Min Range: -7.2216
Max Act: 7.2216. Min Act: -0.1700
Data Index: 8205635 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.5966. Min Act: -0.1700
Data Index: 8205636 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.4716. Min Act: -0.1700
Data Index: 1681943 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.4403. Min Act: -0.1700
Data Index: 2318912 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.4091. Min Act: -0.1700
Data Index: 6986889 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.3153. Min Act: -0.1700
Data Index: 1815665 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.3153. Min Act: -0.1700
Data Index: 1340316 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.2841. Min Act: -0.1700
Data Index: 868556 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.2528. Min Act: -0.1700
Data Index: 1932896 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.2216. Min Act: -0.1700
Data Index: 6922011 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.2528. Min Act: -0.1700
Data Index: 458484 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.2216. Min Act: -0.1700
Data Index: 1940552 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.2216. Min Act: -0.1700
Data Index: 2638198 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.1903. Min Act: -0.1700
Data Index: 6781835 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.1591. Min Act: -0.1700
Data Index: 5228132 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.1278. Min Act: -0.1700
Data Index: 4017481 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.0966. Min Act: -0.1700
Data Index: 5359754 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.1278. Min Act: -0.1700
Data Index: 7082613 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.0966. Min Act: -0.1700
Data Index: 3146163 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2216. Min Range: -7.2216
Max Act: 6.0966. Min Act: -0.1700
Data Index: 4668597 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19