Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.8538. Min Act: -0.1700
Data Index: 1989246 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.7913. Min Act: -0.1700
Data Index: 8541053 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.6663. Min Act: -0.1700
Data Index: 7424988 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.5100. Min Act: -0.1700
Data Index: 2159402 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.5100. Min Act: -0.1700
Data Index: 6308537 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.4475. Min Act: -0.1700
Data Index: 2075543 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.4475. Min Act: -0.1700
Data Index: 5209224 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.4475. Min Act: -0.1700
Data Index: 8729384 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.4163. Min Act: -0.1700
Data Index: 8510455 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.3850. Min Act: -0.1700
Data Index: 8496718 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.3850. Min Act: -0.1700
Data Index: 689710 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.3850. Min Act: -0.1700
Data Index: 3147066 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.3225. Min Act: -0.1700
Data Index: 2791844 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.3225. Min Act: -0.1700
Data Index: 5537121 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.2913. Min Act: -0.1700
Data Index: 1447326 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.2913. Min Act: -0.1700
Data Index: 6389021 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.2913. Min Act: -0.1700
Data Index: 3768294 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.2600. Min Act: -0.1700
Data Index: 1447323 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.2600. Min Act: -0.1700
Data Index: 5575808 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8538. Min Range: -6.8538
Max Act: 6.1975. Min Act: -0.1700
Data Index: 4284458 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19