Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.2855. Min Act: -0.1700
Data Index: 7111477 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.2230. Min Act: -0.1700
Data Index: 7886889 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.2230. Min Act: -0.1700
Data Index: 5836836 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.1605. Min Act: -0.1700
Data Index: 4303826 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.2230. Min Act: -0.1700
Data Index: 7299312 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.1293. Min Act: -0.1700
Data Index: 1069658 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.0980. Min Act: -0.1700
Data Index: 7595815 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.0355. Min Act: -0.1700
Data Index: 1491247 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2855. Min Range: -7.2855
Max Act: 7.0043. Min Act: -0.1700
Data Index: 1365905 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.9730. Min Act: -0.1700
Data Index: 7753911 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.9730. Min Act: -0.1700
Data Index: 7930923 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.9418. Min Act: -0.1700
Data Index: 4052015 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.9418. Min Act: -0.1700
Data Index: 5695170 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.9730. Min Act: -0.1700
Data Index: 8038570 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.9418. Min Act: -0.1700
Data Index: 2668120 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.8793. Min Act: -0.1700
Data Index: 8299200 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.9105. Min Act: -0.1700
Data Index: 8267935 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.8793. Min Act: -0.1700
Data Index: 1913037 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.8480. Min Act: -0.1700
Data Index: 7583348 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2855. Min Range: -7.2855
Max Act: 6.8793. Min Act: -0.1700
Data Index: 3955176 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19