Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3438. Min Range: -5.3438
Max Act: 5.3438. Min Act: -0.1700
Data Index: 4023546 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3438. Min Range: -5.3438
Max Act: 5.0626. Min Act: -0.1700
Data Index: 6742712 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8751. Min Act: -0.1700
Data Index: 2023286 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.9063. Min Act: -0.1700
Data Index: 4406772 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.9063. Min Act: -0.1700
Data Index: 8643362 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8438. Min Act: -0.1700
Data Index: 1223327 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8751. Min Act: -0.1700
Data Index: 4518317 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.9063. Min Act: -0.1700
Data Index: 6991342 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8751. Min Act: -0.1700
Data Index: 3590401 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8438. Min Act: -0.1700
Data Index: 4406751 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8751. Min Act: -0.1700
Data Index: 1912097 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8126. Min Act: -0.1700
Data Index: 4658168 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8438. Min Act: -0.1700
Data Index: 7599911 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.7813. Min Act: -0.1700
Data Index: 4030750 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.7501. Min Act: -0.1700
Data Index: 1210482 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.7501. Min Act: -0.1700
Data Index: 1834742 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8126. Min Act: -0.1700
Data Index: 4414273 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.7501. Min Act: -0.1700
Data Index: 5140242 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.7501. Min Act: -0.1700
Data Index: 3438782 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3438. Min Range: -5.3438
Max Act: 4.8126. Min Act: -0.1700
Data Index: 3514843 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19