Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.5087. Min Act: -0.1700
Data Index: 8191028 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.4775. Min Act: -0.1700
Data Index: 598032 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.3837. Min Act: -0.1700
Data Index: 6886320 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.3212. Min Act: -0.1700
Data Index: 5952948 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.1650. Min Act: -0.1700
Data Index: 8256149 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.0712. Min Act: -0.1700
Data Index: 2872460 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.0087. Min Act: -0.1700
Data Index: 4164666 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.0712. Min Act: -0.1700
Data Index: 5655609 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.0400. Min Act: -0.1700
Data Index: 6886323 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.0712. Min Act: -0.1700
Data Index: 2832725 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.0087. Min Act: -0.1700
Data Index: 3331101 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5087. Min Range: -7.5087
Max Act: 6.9775. Min Act: -0.1700
Data Index: 30949 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5087. Min Range: -7.5087
Max Act: 6.9462. Min Act: -0.1700
Data Index: 6773164 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5087. Min Range: -7.5087
Max Act: 7.0400. Min Act: -0.1700
Data Index: 7624732 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5087. Min Range: -7.5087
Max Act: 6.9462. Min Act: -0.1700
Data Index: 5470777 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5087. Min Range: -7.5087
Max Act: 6.9775. Min Act: -0.1700
Data Index: 6517798 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5087. Min Range: -7.5087
Max Act: 6.9775. Min Act: -0.1700
Data Index: 290755 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5087. Min Range: -7.5087
Max Act: 6.9150. Min Act: -0.1700
Data Index: 6687864 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5087. Min Range: -7.5087
Max Act: 6.8525. Min Act: -0.1700
Data Index: 7063267 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5087. Min Range: -7.5087
Max Act: 6.9462. Min Act: -0.1700
Data Index: 1495406 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19