Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0102. Min Range: -4.0102
Max Act: 4.0102. Min Act: -0.1700
Data Index: 6308257 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0102. Min Range: -4.0102
Max Act: 4.0102. Min Act: -0.1700
Data Index: 7397072 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.9164. Min Act: -0.1700
Data Index: 3599175 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.9164. Min Act: -0.1700
Data Index: 6801080 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.9477. Min Act: -0.1700
Data Index: 4873123 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8851. Min Act: -0.1700
Data Index: 3196474 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8851. Min Act: -0.1700
Data Index: 4287737 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8851. Min Act: -0.1700
Data Index: 3228095 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8539. Min Act: -0.1700
Data Index: 2673223 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8382. Min Act: -0.1700
Data Index: 3219643 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8226. Min Act: -0.1700
Data Index: 6065092 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8226. Min Act: -0.1700
Data Index: 3254176 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8070. Min Act: -0.1700
Data Index: 3297148 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7913. Min Act: -0.1700
Data Index: 1765175 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7913. Min Act: -0.1700
Data Index: 1535181 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7757. Min Act: -0.1700
Data Index: 5809084 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7757. Min Act: -0.1700
Data Index: 2995674 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7913. Min Act: -0.1700
Data Index: 103007 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7757. Min Act: -0.1700
Data Index: 7548462 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7913. Min Act: -0.1700
Data Index: 5343572 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19