Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0817. Min Range: -8.0817
Max Act: 8.0817. Min Act: -0.1700
Data Index: 3704138 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.9879. Min Act: -0.1700
Data Index: 2595551 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.9254. Min Act: -0.1700
Data Index: 387474 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.8942. Min Act: -0.1700
Data Index: 2452936 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.8942. Min Act: -0.1700
Data Index: 2852010 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.8317. Min Act: -0.1700
Data Index: 3372805 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.7692. Min Act: -0.1700
Data Index: 242546 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.8004. Min Act: -0.1700
Data Index: 4859410 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.7067. Min Act: -0.1700
Data Index: 1807803 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.7067. Min Act: -0.1700
Data Index: 510988 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.6754. Min Act: -0.1700
Data Index: 60289 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5817. Min Act: -0.1700
Data Index: 77969 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5504. Min Act: -0.1700
Data Index: 6977772 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5817. Min Act: -0.1700
Data Index: 8094840 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5504. Min Act: -0.1700
Data Index: 142535 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5817. Min Act: -0.1700
Data Index: 6960173 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5192. Min Act: -0.1700
Data Index: 4646017 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5192. Min Act: -0.1700
Data Index: 138491 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5192. Min Act: -0.1700
Data Index: 8436815 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0817. Min Range: -8.0817
Max Act: 7.5192. Min Act: -0.1700
Data Index: 820258 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19