Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6344 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0588. Min Range: -5.0588
Max Act: 5.0588. Min Act: -0.1700
Data Index: 5237369 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0588. Min Range: -5.0588
Max Act: 5.0276. Min Act: -0.1700
Data Index: 4290810 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0588. Min Range: -5.0588
Max Act: 5.0276. Min Act: -0.1700
Data Index: 5757621 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.9651. Min Act: -0.1700
Data Index: 4256152 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.9338. Min Act: -0.1700
Data Index: 176660 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.9026. Min Act: -0.1700
Data Index: 4715228 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.9026. Min Act: -0.1700
Data Index: 7006797 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.9026. Min Act: -0.1700
Data Index: 3017826 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.8713. Min Act: -0.1700
Data Index: 3259199 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.8713. Min Act: -0.1700
Data Index: 872956 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.8088. Min Act: -0.1700
Data Index: 5641890 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.7776. Min Act: -0.1700
Data Index: 8133768 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.7776. Min Act: -0.1700
Data Index: 3011669 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.8088. Min Act: -0.1700
Data Index: 4674091 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.7776. Min Act: -0.1700
Data Index: 6354953 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.8088. Min Act: -0.1700
Data Index: 649255 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.7776. Min Act: -0.1700
Data Index: 6371245 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.7776. Min Act: -0.1700
Data Index: 6249020 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.7776. Min Act: -0.1700
Data Index: 3203716 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0588. Min Range: -5.0588
Max Act: 4.7776. Min Act: -0.1700
Data Index: 4905327 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19