Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0970. Min Act: -0.1700
Data Index: 1706501 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0970. Min Act: -0.1700
Data Index: 3648047 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0657. Min Act: -0.1700
Data Index: 311992 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0657. Min Act: -0.1700
Data Index: 5627521 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0657. Min Act: -0.1700
Data Index: 8481044 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0970. Min Act: -0.1700
Data Index: 1076365 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0345. Min Act: -0.1700
Data Index: 1118496 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0345. Min Act: -0.1700
Data Index: 3097611 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0032. Min Act: -0.1700
Data Index: 4570182 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0032. Min Act: -0.1700
Data Index: 2596953 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0970. Min Range: -5.0970
Max Act: 5.0032. Min Act: -0.1700
Data Index: 5940125 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.9720. Min Act: -0.1700
Data Index: 5807951 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.9720. Min Act: -0.1700
Data Index: 7080460 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.9720. Min Act: -0.1700
Data Index: 1822209 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.9407. Min Act: -0.1700
Data Index: 3324217 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.9407. Min Act: -0.1700
Data Index: 3493503 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.9095. Min Act: -0.1700
Data Index: 5034432 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.8782. Min Act: -0.1700
Data Index: 250075 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.9095. Min Act: -0.1700
Data Index: 2175282 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0970. Min Range: -5.0970
Max Act: 4.9095. Min Act: -0.1700
Data Index: 8051857 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19