Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0766. Min Range: -4.0766
Max Act: 4.0766. Min Act: -0.1700
Data Index: 257503 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0766. Min Range: -4.0766
Max Act: 4.0453. Min Act: -0.1700
Data Index: 6279805 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0766. Min Range: -4.0766
Max Act: 4.0453. Min Act: -0.1700
Data Index: 7643705 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0766. Min Range: -4.0766
Max Act: 4.0453. Min Act: -0.1700
Data Index: 8001823 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9516. Min Act: -0.1700
Data Index: 6078050 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9516. Min Act: -0.1700
Data Index: 1257270 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9203. Min Act: -0.1700
Data Index: 2442425 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9203. Min Act: -0.1700
Data Index: 195721 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9203. Min Act: -0.1700
Data Index: 4485483 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8890. Min Act: -0.1700
Data Index: 446989 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8890. Min Act: -0.1700
Data Index: 8443080 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8890. Min Act: -0.1700
Data Index: 8019054 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8890. Min Act: -0.1700
Data Index: 1342906 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8890. Min Act: -0.1700
Data Index: 2219871 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8890. Min Act: -0.1700
Data Index: 810354 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8578. Min Act: -0.1700
Data Index: 6146675 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8890. Min Act: -0.1700
Data Index: 7238346 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9203. Min Act: -0.1700
Data Index: 257502 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8578. Min Act: -0.1700
Data Index: 2733682 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8578. Min Act: -0.1700
Data Index: 5615632 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19