Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3711 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4327. Min Range: -9.4327
Max Act: 9.4327. Min Act: -0.1700
Data Index: 7964850 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4327. Min Range: -9.4327
Max Act: 9.1827. Min Act: -0.1700
Data Index: 3122582 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4327. Min Range: -9.4327
Max Act: 9.1827. Min Act: -0.1700
Data Index: 6512588 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4327. Min Range: -9.4327
Max Act: 9.1202. Min Act: -0.1700
Data Index: 3318020 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4327. Min Range: -9.4327
Max Act: 9.1202. Min Act: -0.1700
Data Index: 5886781 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4327. Min Range: -9.4327
Max Act: 9.1202. Min Act: -0.1700
Data Index: 8688178 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4327. Min Range: -9.4327
Max Act: 9.0577. Min Act: -0.1700
Data Index: 2066611 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9952. Min Act: -0.1700
Data Index: 3956075 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9952. Min Act: -0.1700
Data Index: 5723611 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9952. Min Act: -0.1700
Data Index: 8638642 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9952. Min Act: -0.1700
Data Index: 7865908 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9327. Min Act: -0.1700
Data Index: 4623462 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9327. Min Act: -0.1700
Data Index: 1769902 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9952. Min Act: -0.1700
Data Index: 8734228 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9327. Min Act: -0.1700
Data Index: 5347348 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9327. Min Act: -0.1700
Data Index: 6018565 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9327. Min Act: -0.1700
Data Index: 427834 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.9327. Min Act: -0.1700
Data Index: 5156506 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.8702. Min Act: -0.1700
Data Index: 2354418 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4327. Min Range: -9.4327
Max Act: 8.8702. Min Act: -0.1700
Data Index: 1779657 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19