Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4484 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2355. Min Range: -11.2355
Max Act: 11.2355. Min Act: -0.1700
Data Index: 3618759 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.8605. Min Act: -0.1700
Data Index: 4097944 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.4230. Min Act: -0.1700
Data Index: 8263490 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.3605. Min Act: -0.1700
Data Index: 5064182 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.4230. Min Act: -0.1700
Data Index: 5734238 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.3605. Min Act: -0.1700
Data Index: 7936229 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.3605. Min Act: -0.1700
Data Index: 107937 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.2980. Min Act: -0.1700
Data Index: 7415186 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.2355. Min Act: -0.1700
Data Index: 6478800 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.2355. Min Act: -0.1700
Data Index: 4686494 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.1105. Min Act: -0.1700
Data Index: 7849874 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.1730. Min Act: -0.1700
Data Index: 5724965 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.1730. Min Act: -0.1700
Data Index: 7934779 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.1105. Min Act: -0.1700
Data Index: 6606140 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.1730. Min Act: -0.1700
Data Index: 1269664 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.0480. Min Act: -0.1700
Data Index: 8228956 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.0480. Min Act: -0.1700
Data Index: 1747738 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.0480. Min Act: -0.1700
Data Index: 3610808 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.0480. Min Act: -0.1700
Data Index: 4481136 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2355. Min Range: -11.2355
Max Act: 10.0480. Min Act: -0.1700
Data Index: 787150 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19