Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.4463. Min Act: -0.1700
Data Index: 8667736 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.2900. Min Act: -0.1700
Data Index: 7016786 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.2275. Min Act: -0.1700
Data Index: 3086035 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.1338. Min Act: -0.1700
Data Index: 9311 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.1025. Min Act: -0.1700
Data Index: 7896906 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.0400. Min Act: -0.1700
Data Index: 4572085 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.0400. Min Act: -0.1700
Data Index: 4182996 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.0088. Min Act: -0.1700
Data Index: 5641350 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4463. Min Range: -6.4463
Max Act: 6.0088. Min Act: -0.1700
Data Index: 3714416 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.9775. Min Act: -0.1700
Data Index: 8382857 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.9775. Min Act: -0.1700
Data Index: 6247 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.9463. Min Act: -0.1700
Data Index: 4751903 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.9775. Min Act: -0.1700
Data Index: 8640845 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.9463. Min Act: -0.1700
Data Index: 8110937 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.9463. Min Act: -0.1700
Data Index: 790989 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.9463. Min Act: -0.1700
Data Index: 2678471 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.9150. Min Act: -0.1700
Data Index: 4665644 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.8838. Min Act: -0.1700
Data Index: 4598234 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.8838. Min Act: -0.1700
Data Index: 2124399 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4463. Min Range: -6.4463
Max Act: 5.8838. Min Act: -0.1700
Data Index: 1981350 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19