Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.9600. Min Act: -0.1700
Data Index: 8613698 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.9600. Min Act: -0.1700
Data Index: 2097781 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.9287. Min Act: -0.1700
Data Index: 2319280 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.9600. Min Act: -0.1700
Data Index: 975594 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8818. Min Act: -0.1700
Data Index: 1992915 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8975. Min Act: -0.1700
Data Index: 569616 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8662. Min Act: -0.1700
Data Index: 5779422 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8662. Min Act: -0.1700
Data Index: 1697287 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8662. Min Act: -0.1700
Data Index: 4872289 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8662. Min Act: -0.1700
Data Index: 6865837 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8818. Min Act: -0.1700
Data Index: 4454942 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8662. Min Act: -0.1700
Data Index: 2899133 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8662. Min Act: -0.1700
Data Index: 275812 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8818. Min Act: -0.1700
Data Index: 1198577 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8506. Min Act: -0.1700
Data Index: 1933945 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8506. Min Act: -0.1700
Data Index: 3041409 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8193. Min Act: -0.1700
Data Index: 4946660 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8036. Min Act: -0.1700
Data Index: 1128446 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8193. Min Act: -0.1700
Data Index: 2346585 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9600. Min Range: -3.9600
Max Act: 3.8193. Min Act: -0.1700
Data Index: 1060227 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19