Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5652 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0664. Min Range: -7.0664
Max Act: 7.0664. Min Act: -0.1700
Data Index: 8638073 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.9727. Min Act: -0.1700
Data Index: 3460459 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.9414. Min Act: -0.1700
Data Index: 7601754 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.9102. Min Act: -0.1700
Data Index: 5775259 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.8164. Min Act: -0.1700
Data Index: 3355228 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.7852. Min Act: -0.1700
Data Index: 5327224 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.7539. Min Act: -0.1700
Data Index: 8699878 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6914. Min Act: -0.1700
Data Index: 699099 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6914. Min Act: -0.1700
Data Index: 5023428 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6914. Min Act: -0.1700
Data Index: 5770209 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6602. Min Act: -0.1700
Data Index: 5862450 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6914. Min Act: -0.1700
Data Index: 5614028 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6289. Min Act: -0.1700
Data Index: 1989750 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6289. Min Act: -0.1700
Data Index: 658103 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6289. Min Act: -0.1700
Data Index: 81412 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.6289. Min Act: -0.1700
Data Index: 6158412 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.5977. Min Act: -0.1700
Data Index: 397131 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.5977. Min Act: -0.1700
Data Index: 3267773 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.5977. Min Act: -0.1700
Data Index: 5190799 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0664. Min Range: -7.0664
Max Act: 6.5664. Min Act: -0.1700
Data Index: 2690067 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19