Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4945 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.6250. Min Act: -0.1700
Data Index: 109381 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.6250. Min Act: -0.1700
Data Index: 7537245 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.4062. Min Act: -0.1700
Data Index: 8787843 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.4062. Min Act: -0.1700
Data Index: 5527605 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.3750. Min Act: -0.1700
Data Index: 8003138 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.3437. Min Act: -0.1700
Data Index: 31915 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.3125. Min Act: -0.1700
Data Index: 6474090 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.2812. Min Act: -0.1700
Data Index: 4325330 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.2500. Min Act: -0.1700
Data Index: 1379736 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.2187. Min Act: -0.1700
Data Index: 3767289 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.2187. Min Act: -0.1700
Data Index: 8193709 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.1562. Min Act: -0.1700
Data Index: 6048322 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.1562. Min Act: -0.1700
Data Index: 6313630 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.1562. Min Act: -0.1700
Data Index: 6238785 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.1250. Min Act: -0.1700
Data Index: 92106 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.0625. Min Act: -0.1700
Data Index: 599884 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.0937. Min Act: -0.1700
Data Index: 5750809 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.0937. Min Act: -0.1700
Data Index: 418559 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.0625. Min Act: -0.1700
Data Index: 4444976 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6250. Min Range: -7.6250
Max Act: 7.0625. Min Act: -0.1700
Data Index: 7428369 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19