Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.2509. Min Act: -0.1700
Data Index: 4371329 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.2196. Min Act: -0.1700
Data Index: 275559 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.2196. Min Act: -0.1700
Data Index: 2312416 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.0946. Min Act: -0.1700
Data Index: 3959482 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.0946. Min Act: -0.1700
Data Index: 5849000 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.0321. Min Act: -0.1700
Data Index: 565391 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.0946. Min Act: -0.1700
Data Index: 1428039 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.0009. Min Act: -0.1700
Data Index: 877895 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.0009. Min Act: -0.1700
Data Index: 6619513 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2509. Min Range: -5.2509
Max Act: 5.0009. Min Act: -0.1700
Data Index: 6619499 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.9696. Min Act: -0.1700
Data Index: 1041255 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.9384. Min Act: -0.1700
Data Index: 4562703 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.9071. Min Act: -0.1700
Data Index: 7073103 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.9071. Min Act: -0.1700
Data Index: 6492019 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.9071. Min Act: -0.1700
Data Index: 5645945 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.9696. Min Act: -0.1700
Data Index: 6619496 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.9071. Min Act: -0.1700
Data Index: 2281518 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.8759. Min Act: -0.1700
Data Index: 2081538 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.8759. Min Act: -0.1700
Data Index: 5761119 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2509. Min Range: -5.2509
Max Act: 4.8446. Min Act: -0.1700
Data Index: 3973348 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19