Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0299. Min Range: -6.0299
Max Act: 6.0299. Min Act: -0.1700
Data Index: 2322654 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.9362. Min Act: -0.1700
Data Index: 2510568 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.8424. Min Act: -0.1700
Data Index: 239609 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.8737. Min Act: -0.1700
Data Index: 6852262 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.8424. Min Act: -0.1700
Data Index: 363452 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.7799. Min Act: -0.1700
Data Index: 7308676 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.8112. Min Act: -0.1700
Data Index: 2666921 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.7799. Min Act: -0.1700
Data Index: 5182232 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.7487. Min Act: -0.1700
Data Index: 8481481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.7799. Min Act: -0.1700
Data Index: 1645822 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.7174. Min Act: -0.1700
Data Index: 2214812 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.7174. Min Act: -0.1700
Data Index: 1588587 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.6549. Min Act: -0.1700
Data Index: 6160690 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.6549. Min Act: -0.1700
Data Index: 7668851 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.6549. Min Act: -0.1700
Data Index: 7334133 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.6549. Min Act: -0.1700
Data Index: 754284 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.6549. Min Act: -0.1700
Data Index: 1915430 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.6237. Min Act: -0.1700
Data Index: 2734197 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.5924. Min Act: -0.1700
Data Index: 3664997 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0299. Min Range: -6.0299
Max Act: 5.6237. Min Act: -0.1700
Data Index: 7144075 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19