Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4766 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.8720. Min Act: -0.1700
Data Index: 3038736 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.6220. Min Act: -0.1700
Data Index: 976704 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.6220. Min Act: -0.1700
Data Index: 8104804 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.4970. Min Act: -0.1700
Data Index: 3989685 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.4970. Min Act: -0.1700
Data Index: 8345777 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.3407. Min Act: -0.1700
Data Index: 1101253 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.2782. Min Act: -0.1700
Data Index: 1627635 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.3095. Min Act: -0.1700
Data Index: 4160503 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.2470. Min Act: -0.1700
Data Index: 6178835 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.2157. Min Act: -0.1700
Data Index: 814666 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.2470. Min Act: -0.1700
Data Index: 7609671 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.1845. Min Act: -0.1700
Data Index: 8473588 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.1845. Min Act: -0.1700
Data Index: 1333566 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.1845. Min Act: -0.1700
Data Index: 2075722 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.1532. Min Act: -0.1700
Data Index: 7928412 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.1532. Min Act: -0.1700
Data Index: 1067125 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.1220. Min Act: -0.1700
Data Index: 2637081 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.0907. Min Act: -0.1700
Data Index: 5569183 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.0595. Min Act: -0.1700
Data Index: 5399877 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8720. Min Range: -6.8720
Max Act: 6.0595. Min Act: -0.1700
Data Index: 5391363 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19